Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20931
    Prev
    Next
    INDEX
    Explanations

    words related to expectations or judgments of oneself or others

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" and its various forms, indicating a focus on existence or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dispute
    -0.64
     Falk
    -0.57
     Frey
    -0.55
     Wol
    -0.54
     sweat
    -0.53
     Wid
    -0.53
     Boll
    -0.53
     Gum
    -0.52
     Wick
    -0.52
     Gul
    -0.51
    POSITIVE LOGITS
     able
    0.96
     anyways
    0.88
    .
    0.83
    held
    0.81
    .#
    0.80
     anyway
    0.79
     when
    0.78
    !!!!!!!!
    0.78
    !.
    0.76
    ecause
    0.74
    Activations Density 0.089%

    No Known Activations