© 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. 3-RES-JB
    11. 6333
    Prev
    Next
    INDEX
    Explanations

    phrases referring to general tendencies or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mostly" indicating a common or general occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.77
    retched
    -0.76
    alid
    -0.71
    anth
    -0.71
    iry
    -0.70
    iggins
    -0.70
    orse
    -0.68
    eem
    -0.68
    yle
    -0.68
     Commissioners
    -0.67
    POSITIVE LOGITS
     consisted
    0.90
     consist
    0.90
     revolves
    0.84
     consists
    0.82
     comprised
    0.81
     lacking
    0.80
     consisting
    0.78
     disappoint
    0.72
     aimed
    0.71
    tenance
    0.70
    Activations Density 0.017%

    No Known Activations