© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1121
    Prev
    Next
    INDEX
    Explanations

    names or phrases related to a specific individual named Benoit or a place or thing called "Metaspl" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with definitions or detailed descriptions

    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
     Blazing
    -0.67
     Burgess
    -0.65
    chlor
    -0.64
    glers
    -0.63
    worm
    -0.62
     Scorp
    -0.62
     Cycl
    -0.61
     thr
    -0.61
    worms
    -0.61
     squid
    -0.61
    POSITIVE LOGITS
    oit
    3.06
    rait
    2.31
    lection
    1.62
    oin
    1.46
    raits
    1.31
    lections
    1.16
    LEASE
    0.98
    ishment
    0.95
    ilion
    0.93
    ause
    0.93
    Activations Density 0.034%

    No Known Activations