© 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. 4-RES-JB
    11. 10959
    Prev
    Next
    INDEX
    Explanations

    commands or instructions related to creating, adding, and managing various elements in a database or software development environment

    oai_token-act-pair · gpt-3.5-turbo

    commands or instructions related to creating or generating resources in a programming context

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

    No Comments

    Negative Logits
    Bey
    -0.76
     preached
    -0.73
    osate
    -0.69
    atti
    -0.63
    phia
    -0.63
     preach
    -0.61
    auld
    -0.61
    entimes
    -0.60
    Thom
    -0.60
    hirt
    -0.60
    POSITIVE LOGITS
    Instance
    0.79
    slave
    0.78
     Export
    0.74
    ãĥ¼ãĥĨãĤ£
    0.73
    urable
    0.72
    ividual
    0.72
    ezvous
    0.70
     Router
    0.70
     batch
    0.70
    sequence
    0.69
    Activations Density 0.035%

    No Known Activations