© 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. 1175
    Prev
    Next
    INDEX
    Explanations

    words related to locations or spaces located away from central areas or edges

    oai_token-act-pair · gpt-3.5-turbo

    words related to edges or boundaries

    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
     ROCK
    -0.64
     POWER
    -0.64
     Destroy
    -0.63
     ATK
    -0.60
     SUP
    -0.59
    bourg
    -0.58
    OTA
    -0.58
     bait
    -0.57
     hypnot
    -0.57
     DIRECT
    -0.57
    POSITIVE LOGITS
    inges
    4.07
    inged
    1.71
    rium
    1.19
    agher
    1.15
     periphery
    0.94
     outset
    0.87
    opian
    0.85
    irez
    0.84
    unal
    0.82
    eteria
    0.80
    Activations Density 0.034%

    No Known Activations