© 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. 2700
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "In all."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote totality or universality related to specific contexts or subjects

    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
    lash
    -0.68
    yip
    -0.68
    rouse
    -0.67
    ALLY
    -0.67
    erald
    -0.66
     scapego
    -0.64
     Cumm
    -0.62
    osate
    -0.62
    stall
    -0.61
    rift
    -0.60
    POSITIVE LOGITS
     likelihood
    1.03
     respects
    1.03
    usion
    0.92
     seriousness
    0.89
    ocating
    0.89
     cases
    0.88
     manner
    0.86
     directions
    0.84
     fairness
    0.84
     honesty
    0.83
    Activations Density 0.038%

    No Known Activations