© 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. 6164
    Prev
    Next
    INDEX
    Explanations

    scientific or biological terms and names of plant or animal species

    oai_token-act-pair · gpt-3.5-turbo

    biological entities and classifications

    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
    DragonMagazine
    -0.80
     GEAR
    -0.79
    soDeliveryDate
    -0.79
    WIND
    -0.75
    blogs
    -0.71
    Gear
    -0.70
    Weapons
    -0.68
    staking
    -0.67
    selves
    -0.67
    Money
    -0.67
    POSITIVE LOGITS
    ensis
    1.75
    iens
    1.05
    orum
    1.01
    iae
    0.99
    osa
    0.98
    icus
    0.98
    atus
    0.93
    icum
    0.87
    iatus
    0.84
    ii
    0.82
    Activations Density 0.152%

    No Known Activations