© 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. 0-RES-JB
    11. 1166
    Prev
    Next
    INDEX
    Explanations

    terms related to borrowing or lending

    oai_token-act-pair · gpt-3.5-turbo

    terms related to borrowing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acceler
    -0.64
    retty
    -0.63
     temperature
    -0.62
     temperatures
    -0.60
     ecstasy
    -0.60
     glutamate
    -0.60
     pursu
    -0.59
     campaign
    -0.59
     respectively
    -0.59
     accelerator
    -0.58
    POSITIVE LOGITS
    bor
    4.78
    bour
    1.97
    bors
    1.90
    mor
    1.17
    abor
    1.16
    bol
    1.12
    gor
    1.10
    vest
    1.08
    ror
    1.05
    bl
    1.00
    Activations Density 0.004%

    No Known Activations