© 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. 17108
    Prev
    Next
    INDEX
    Explanations

    phrases referring to the collective actions or decisions of a group or organization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "we" and related expressions, indicating a focus on collective action or group involvement

    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
    nesota
    -0.65
    cum
    -0.65
    Appearances
    -0.65
    atory
    -0.62
    netflix
    -0.61
     Ago
    -0.59
    icative
    -0.59
    idium
    -0.59
     Kelvin
    -0.59
    Reviewer
    -0.59
    POSITIVE LOGITS
    're
    1.35
    've
    1.31
    bsite
    1.17
    'll
    1.14
     strive
    1.09
    athered
    1.07
     ourselves
    1.06
    akening
    1.01
    'd
    1.00
    arers
    0.96
    Activations Density 0.258%

    No Known Activations