© 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. 17079
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions or actions, often with a negative connotation

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social justice and emotional experiences

    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
    arnaev
    -0.75
    uscript
    -0.60
    âĸ¬
    -0.58
     Ruins
    -0.57
    zl
    -0.57
    amins
    -0.56
     Crate
    -0.56
    abella
    -0.56
     Kingdoms
    -0.56
    ħĭ
    -0.55
    POSITIVE LOGITS
    lessness
    0.96
     wherein
    0.86
     whereby
    0.85
    fulness
    0.84
    ulence
    0.81
     albeit
    0.76
     insofar
    0.75
     bordering
    0.72
     unmatched
    0.71
     belonging
    0.71
    Activations Density 0.349%

    No Known Activations