© 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. 6618
    Prev
    Next
    INDEX
    Explanations

    technical terms related to hardware performance and specifications

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to components and metrics in systems or devices

    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
    »Ĵ
    -0.79
    odied
    -0.76
     Damn
    -0.73
    earable
    -0.70
    utterstock
    -0.69
    arnaev
    -0.68
    prison
    -0.68
    rolet
    -0.67
     Prison
    -0.65
     Hubbard
    -0.65
    POSITIVE LOGITS
     sizes
    1.49
     size
    1.34
     lengths
    1.25
     width
    1.25
     length
    1.24
     configurations
    1.23
     geometry
    1.19
     thickness
    1.18
     placement
    1.15
     layouts
    1.15
    Activations Density 0.306%

    No Known Activations