© 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. 4-RES-JB
    11. 8609
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental cleanup and hazardous sites known as Superfund sites

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental issues and Superfund sites

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

    No Comments

    Negative Logits
     omission
    -0.82
    cember
    -0.66
     throats
    -0.64
     NEC
    -0.63
     hesitation
    -0.60
     Barron
    -0.59
     Lange
    -0.59
     offence
    -0.59
    sworth
    -0.58
    gow
    -0.58
    POSITIVE LOGITS
    rencies
    0.85
    olester
    0.78
    amins
    0.76
    roid
    0.75
    anium
    0.74
     Telescope
    0.74
    mega
    0.74
    heses
    0.73
    ukong
    0.73
    atch
    0.71
    Activations Density 0.102%

    No Known Activations