© 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. 7-RES-JB
    11. 16514
    Prev
    Next
    INDEX
    Explanations

    email addresses and website URLs

    oai_token-act-pair · gpt-3.5-turbo

    email addresses and social media handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reduction
    -1.03
     Tenth
    -1.01
     Disorder
    -1.00
     Ninth
    -0.98
     Lines
    -0.97
     Fin
    -0.94
     Direction
    -0.93
     Index
    -0.93
     Finder
    -0.93
     Hole
    -0.92
    POSITIVE LOGITS
    olson
    1.07
     americ
    1.05
    izabeth
    0.92
    _
    0.92
    football
    0.91
    brown
    0.91
    pod
    0.89
    @
    0.86
    clinton
    0.85
    ensis
    0.84
    Activations Density 0.174%

    No Known Activations