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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 15751
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions being completed or carried out

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "made" in various contexts related to actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    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_pre
    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
    icals
    -0.70
    hens
    -0.67
    assis
    -0.64
    hov
    -0.60
    ei
    -0.59
     GPA
    -0.58
    CLOSE
    -0.57
    IPS
    -0.57
    hin
    -0.56
     Cong
    -0.55
    POSITIVE LOGITS
     payable
    1.09
     available
    1.08
     possible
    0.90
     public
    0.89
     landfall
    0.85
     aware
    0.84
     abundantly
    0.82
     sure
    0.82
     redundant
    0.81
     accessible
    0.80
    Activations Density 0.068%

    No Known Activations