© 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. 9-RES-JB
    6. 1389
    Prev
    Next
    INDEX
    Explanations

    mentions of identification methods and numbers

    oai_token-act-pair · gpt-3.5-turbo

    requirements and processes related to identification and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    storms
    -0.87
    optim
    -0.84
     explosions
    -0.80
    zinski
    -0.80
     Atmosp
    -0.78
    ovie
    -0.74
    Synopsis
    -0.73
     tumult
    -0.73
    onential
    -0.73
    scenes
    -0.71
    POSITIVE LOGITS
     passport
    1.58
     registration
    1.53
     passports
    1.51
     paperwork
    1.49
     Registration
    1.40
     certificates
    1.35
     certificate
    1.34
     Certificate
    1.29
     authorization
    1.29
     registry
    1.26
    Activations Density 0.743%

    No Known Activations