© 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. 7-RES-JB
    11. 13468
    Prev
    Next
    INDEX
    Explanations

    phrases related to countable items or instances

    oai_token-act-pair · gpt-3.5-turbo

    references to time frames or instances in a recurring context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ersive
    -0.80
    blance
    -0.78
    ertodd
    -0.65
    urer
    -0.64
    uction
    -0.64
     surpr
    -0.63
    leep
    -0.63
    OGR
    -0.63
    lie
    -0.63
    mares
    -0.62
    POSITIVE LOGITS
     Cups
    0.70
    Ocean
    0.67
     course
    0.66
    ãĤ«
    0.65
    Adams
    0.63
     us
    0.63
     successive
    0.63
     Southeast
    0.62
    ses
    0.62
    course
    0.62
    Activations Density 0.047%

    No Known Activations