© 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. 8-RES-JB
    6. 3947
    Prev
    Next
    INDEX
    Explanations

    reptiles and mammals

    oai_token-act-pair · gpt-3.5-turbo

    specimens of animals or unique species

    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
     Policies
    -0.78
    ourses
    -0.78
     Promotion
    -0.74
     PSU
    -0.74
    isSpecialOrderable
    -0.73
     Assets
    -0.71
     Student
    -0.70
     Savings
    -0.69
     Telecommunications
    -0.68
     deferred
    -0.68
    POSITIVE LOGITS
     hiber
    1.27
     extinct
    1.25
     mating
    1.12
     breeding
    1.12
     hunted
    1.12
     genus
    1.11
     domest
    1.10
     grazing
    1.09
     species
    1.06
     bred
    1.06
    Activations Density 0.697%

    No Known Activations