© 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. 2-RES-JB
    11. 23382
    Prev
    Next
    INDEX
    Explanations

    words related to important tasks or issues that need attention or action

    oai_token-act-pair · gpt-3.5-turbo

    references to priorities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.75
    Shock
    -0.73
    techn
    -0.72
    issan
    -0.70
    attering
    -0.70
    semble
    -0.70
    imar
    -0.68
    redited
    -0.68
    idden
    -0.67
    Naz
    -0.67
    POSITIVE LOGITS
     priorities
    1.17
     priority
    0.84
     priorit
    0.81
     allocation
    0.74
     proble
    0.72
     oriented
    0.72
     agenda
    0.71
     checklist
    0.70
     allocations
    0.70
     shaping
    0.69
    Activations Density 0.007%

    No Known Activations