© 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. 11-RES-JB
    11. 9988
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a contrast or continuation of thought

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "there" and its variations, indicating the presence of statements about existence or conditions

    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
    ointed
    -0.64
    ãĥĺ
    -0.63
     comprom
    -0.60
    shoot
    -0.60
    transfer
    -0.59
    rient
    -0.57
    Finish
    -0.57
    insert
    -0.56
    ONSORED
    -0.56
     Seym
    -0.56
    POSITIVE LOGITS
     are
    1.24
     exists
    1.21
     aren
    1.15
     seems
    1.11
    's
    1.11
     appears
    1.10
     ARE
    1.07
     isn
    1.06
     is
    1.06
     exist
    1.03
    Activations Density 0.096%

    No Known Activations