© 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. 8-RES-JB
    11. 22559
    Prev
    Next
    INDEX
    Explanations

    personal statements indicating actions or experiences

    oai_token-act-pair · gpt-3.5-turbo

    distributed forms of the verb "have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Apart
    -0.69
     sidelines
    -0.62
     precursor
    -0.60
    atically
    -0.59
     hey
    -0.58
     Kingdoms
    -0.57
    bery
    -0.57
     debacle
    -0.57
    eus
    -0.57
     guiName
    -0.56
    POSITIVE LOGITS
     been
    1.16
    been
    1.04
     gotten
    1.01
     seen
    0.96
     personally
    0.94
     myself
    0.93
     heard
    0.93
     subscribed
    0.89
     witnessed
    0.89
     spoken
    0.85
    Activations Density 0.178%

    No Known Activations