© 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. 1-RES-JB
    11. 20238
    Prev
    Next
    INDEX
    Explanations

    tasks or activities described in a context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "tasks" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geo
    -0.80
     Vide
    -0.67
     Indian
    -0.62
     Anglo
    -0.61
     RR
    -0.60
     Columbus
    -0.59
     Jal
    -0.58
    IGH
    -0.58
     Rap
    -0.58
     Rail
    -0.56
    POSITIVE LOGITS
     tasks
    1.38
    asks
    1.10
    task
    1.00
     task
    0.99
    pring
    0.93
    ername
    0.92
    Task
    0.89
    irements
    0.86
    ioned
    0.85
     chores
    0.84
    Activations Density 0.008%

    No Known Activations