© 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. 8-RES-JB
    11. 16896
    Prev
    Next
    INDEX
    Explanations

    alternatives or different possibilities

    oai_token-act-pair · gpt-3.5-turbo

    the word "or" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igr
    -0.67
    ERG
    -0.65
    IGHTS
    -0.65
    KER
    -0.65
    estones
    -0.64
    IDENT
    -0.63
    ires
    -0.63
    erg
    -0.63
    onday
    -0.63
    UD
    -0.62
    POSITIVE LOGITS
     alternatively
    1.11
    thodox
    1.04
    Else
    0.95
     worse
    0.93
     rather
    0.93
     whatever
    0.92
    phan
    0.92
     maybe
    0.92
     equival
    0.91
    acular
    0.90
    Activations Density 0.040%

    No Known Activations