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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 12441
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and activities

    oai_token-act-pair · gpt-3.5-turbo

    commas used to segment ideas or clauses in a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odes
    -0.73
    Elsewhere
    -0.65
    èĢħ
    -0.62
    ="
    -0.60
    eele
    -0.60
    lier
    -0.60
    ickets
    -0.59
    ahu
    -0.57
    legates
    -0.55
    izens
    -0.55
    POSITIVE LOGITS
     myself
    1.17
     my
    1.10
     haha
    1.08
     but
    1.00
     hoping
    0.90
     I
    0.88
     wondering
    0.87
    but
    0.84
    my
    0.84
     although
    0.83
    Activations Density 0.304%

    No Known Activations