© 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. 9138
    Prev
    Next
    INDEX
    Explanations

    references to sheep

    oai_token-act-pair · gpt-3.5-turbo

    references to sheep and related terms

    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
    ENTS
    -0.83
    SPONSORED
    -0.78
     fortun
    -0.74
     vehement
    -0.71
     sugg
    -0.70
     indo
    -0.69
     validity
    -0.69
    nce
    -0.68
     millenn
    -0.67
     condem
    -0.67
    POSITIVE LOGITS
    dogs
    1.20
    dog
    1.18
    ishly
    1.16
    skin
    1.06
    poke
    0.96
    bats
    0.89
    folk
    0.88
    bones
    0.85
    ish
    0.84
    stra
    0.84
    Activations Density 0.007%

    No Known Activations