© 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. 10-RES-JB
    11. 24401
    Prev
    Next
    INDEX
    Explanations

    the word "Where" followed by context-related information

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases asking about locations or directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.67
    )].
    -0.64
    ³³³³³³³³
    -0.63
    emon
    -0.61
    SIZE
    -0.53
    interstitial
    -0.52
     grasp
    -0.51
    lator
    -0.51
    bright
    -0.51
     Reef
    -0.51
    POSITIVE LOGITS
    ver
    1.65
    abouts
    1.56
    upon
    1.51
    fore
    1.43
    soever
    1.13
     else
    1.08
    ever
    0.97
    VER
    0.92
    else
    0.92
    after
    0.84
    Activations Density 0.043%

    No Known Activations