© 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. 8-RES-JB
    6. 893
    Prev
    Next
    INDEX
    Explanations

    forms of the word "venue"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "to have" in different 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
    DEP
    -0.67
    arlane
    -0.67
     challeng
    -0.65
     flares
    -0.60
     flare
    -0.60
     Osw
    -0.60
     deliberations
    -0.58
     pse
    -0.58
    ONEY
    -0.58
     Rosenberg
    -0.56
    POSITIVE LOGITS
    ï¸ı
    0.93
    ault
    0.83
    ilver
    0.81
     Rouge
    0.80
     Marketable
    0.78
    edo
    0.76
    oir
    0.75
    ée
    0.75
    oise
    0.74
    tale
    0.74
    Activations Density 0.164%

    No Known Activations