© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 9096
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating positivity or productiveness

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with constructive engagement or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orph
    -0.73
    olog
    -0.71
    ared
    -0.70
    literally
    -0.70
    annis
    -0.69
    atch
    -0.69
    king
    -0.68
    sole
    -0.66
    gars
    -0.66
     Hosp
    -0.65
    POSITIVE LOGITS
     constructive
    1.26
    -+-+
    0.92
     redes
    0.84
     sidx
    0.81
    wcsstore
    0.81
     feedback
    0.79
     entreprene
    0.76
     criticism
    0.75
     contribut
    0.73
    terday
    0.73
    Activations Density 0.012%

    No Known Activations