© 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. 12976
    Prev
    Next
    INDEX
    Explanations

    mention of actions related to funding and financial allocation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to defunding and watering regulations

    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
    robat
    -0.75
    idad
    -0.73
    士
    -0.71
    hift
    -0.69
     drawer
    -0.68
    ioned
    -0.66
     Pike
    -0.66
    olson
    -0.66
    Domain
    -0.64
     inquest
    -0.64
    POSITIVE LOGITS
    pling
    0.74
    mentation
    0.73
    adow
    0.72
    xual
    0.70
    hovah
    0.68
    OHN
    0.68
    bler
    0.68
     watering
    0.67
     Hort
    0.67
    elled
    0.65
    Activations Density 0.023%

    No Known Activations