© 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. 754
    Prev
    Next
    INDEX
    Explanations

    names of people, specifically focusing on last names

    oai_token-act-pair · gpt-3.5-turbo

    names, particularly last names, associated with notable individuals

    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
    ktop
    -0.71
     srfAttach
    -0.71
     VIDE
    -0.66
    ModLoader
    -0.66
     BOX
    -0.63
     Fancy
    -0.63
     ANGEL
    -0.63
     Serie
    -0.62
     polarization
    -0.62
    ILA
    -0.62
    POSITIVE LOGITS
    hart
    1.15
    gren
    1.14
    quist
    1.13
    hardt
    1.12
    hoff
    1.12
    hill
    1.11
    enberg
    1.07
    cott
    1.05
    baugh
    1.04
    shaw
    1.02
    Activations Density 0.156%

    No Known Activations