© 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. 17290
    Prev
    Next
    INDEX
    Explanations

    text-related entities and interactions in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to textual content and messaging

    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
     Ern
    -0.72
    CVE
    -0.67
     CVE
    -0.66
    ^^^^
    -0.65
    ulic
    -0.65
    BLIC
    -0.65
    kins
    -0.63
    vernment
    -0.62
    ño
    -0.61
    kus
    -0.61
    POSITIVE LOGITS
    ured
    1.49
    uring
    1.22
    area
    1.18
    iles
    1.17
    ural
    1.16
    uality
    1.15
    ures
    1.15
     messaging
    1.05
    ually
    1.05
     messages
    1.02
    Activations Density 0.032%

    No Known Activations