© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 3616
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions about particular actions or behaviors by various individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases or constructs that emphasize location or presence within a space or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lash
    -0.68
    strom
    -0.60
    ieth
    -0.58
    isan
    -0.56
    etic
    -0.55
     harshly
    -0.53
    wolves
    -0.52
    cale
    -0.52
    norm
    -0.52
    ction
    -0.52
    POSITIVE LOGITS
     tow
    1.45
     mind
    1.29
     hand
    1.10
     abundance
    1.01
    mind
    0.84
    ked
    0.82
     place
    0.81
    hand
    0.80
     reserve
    0.79
    İĭ
    0.77
    Activations Density 0.177%

    No Known Activations