© 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. 9247
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or disappointments

    oai_token-act-pair · gpt-3.5-turbo

    references to summer

    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
    ICLE
    -0.81
    PLA
    -0.80
    RAW
    -0.77
    Cra
    -0.71
    avorite
    -0.70
    ivist
    -0.68
    ij
    -0.67
    eq
    -0.66
    ocre
    -0.66
    Cu
    -0.64
    POSITIVE LOGITS
    ummer
    1.05
    iannopoulos
    0.85
    cair
    0.81
     Scouting
    0.70
    fest
    0.69
    swer
    0.69
    é¾įåĸļ士
    0.68
    ity
    0.68
    dayName
    0.67
    iann
    0.67
    Activations Density 0.016%

    No Known Activations