© 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. 22625
    Prev
    Next
    INDEX
    Explanations

    animals and creatures

    oai_token-act-pair · gpt-3.5-turbo

    names of various animal 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
    oppable
    -0.78
    ij士
    -0.74
    ettings
    -0.71
    )=(
    -0.69
    ories
    -0.67
    quickShipAvailable
    -0.67
    ession
    -0.66
    leeve
    -0.66
    stanbul
    -0.66
    Effective
    -0.65
    POSITIVE LOGITS
     carc
    1.22
     species
    1.06
     beetle
    1.05
     pup
    1.05
     habitat
    1.03
     calf
    1.00
     hunter
    0.97
     cub
    0.94
     mascot
    0.94
     hiber
    0.94
    Activations Density 0.254%

    No Known Activations