© 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. 12116
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to advertisements or promotions

    oai_token-act-pair · gpt-3.5-turbo
    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
     favourites
    -0.37
    nered
    -0.34
     civilisation
    -0.31
     organising
    -0.30
     organisations
    -0.30
     organisation
    -0.29
     defences
    -0.29
     organisers
    -0.29
    verts
    -0.28
     signalling
    -0.28
    POSITIVE LOGITS
    rosso
    0.32
    JUST
    0.30
    phalt
    0.28
     Keystone
    0.27
     NASCAR
    0.27
     Hurricane
    0.26
     Miami
    0.26
     Palm
    0.26
     Romo
    0.26
     Aerial
    0.26
    Activations Density 2.824%

    No Known Activations