© 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. 3-RES-JB
    11. 7030
    Prev
    Next
    INDEX
    Explanations

    text related to environmental contamination and cleanup, particularly Superfund sites

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental and economic issues associated with Superfund sites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     omission
    -0.78
     offence
    -0.73
     weakness
    -0.72
     McMaster
    -0.69
     Barron
    -0.68
     NEC
    -0.66
    ĸļ
    -0.65
     pse
    -0.65
     underlying
    -0.63
     Neh
    -0.63
    POSITIVE LOGITS
    maxwell
    0.86
    arming
    0.85
    rencies
    0.85
    natureconservancy
    0.83
    roid
    0.82
    olester
    0.80
    incial
    0.79
    itton
    0.79
    iolet
    0.78
    ÃŁ
    0.75
    Activations Density 0.136%

    No Known Activations