© 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. 10282
    Prev
    Next
    INDEX
    Explanations

    phrases related to sharing commonality or kinship

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to kinship and connections among people

    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
    ©¶æ
    -0.78
    uden
    -0.75
    rique
    -0.74
    atton
    -0.73
    omy
    -0.68
    atra
    -0.66
    orius
    -0.66
    bered
    -0.66
    bers
    -0.66
    zed
    -0.65
    POSITIVE LOGITS
     spirits
    1.16
     kindred
    1.11
     souls
    0.88
     vein
    0.82
     fractions
    0.80
    luaj
    0.80
     spirit
    0.78
     strugg
    0.76
     ancestors
    0.75
     kins
    0.75
    Activations Density 0.009%

    No Known Activations