© 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. 3-RES-JB
    6. 12175
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICAN
    -0.77
    disabled
    -0.75
    href
    -0.72
    Lear
    -0.72
    Grant
    -0.71
    Reviewer
    -0.71
    FontSize
    -0.70
    Parser
    -0.69
    ILLE
    -0.68
    Contents
    -0.67
    POSITIVE LOGITS
     Aven
    0.74
    rone
    0.71
     Eve
    0.70
     Kali
    0.68
    rist
    0.67
    aliation
    0.66
     Stab
    0.66
     Utt
    0.65
     Sister
    0.65
     Jaw
    0.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.