© 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. 0-RES-JB
    11. 22295
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to collages

    oai_token-act-pair · gpt-3.5-turbo

    terms related to collaboration and collective or mixed media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akings
    -0.91
     Throne
    -0.81
     Demand
    -0.75
    umption
    -0.73
    onement
    -0.73
     Parad
    -0.72
    akia
    -0.70
     Stronghold
    -0.69
    ardless
    -0.69
    izational
    -0.68
    POSITIVE LOGITS
     coll
    3.99
    coll
    1.82
    Coll
    1.49
     collide
    1.38
     Coll
    1.38
     collar
    1.33
     collision
    1.19
     collisions
    1.16
     collided
    1.14
     collusion
    1.09
    Activations Density 0.006%

    No Known Activations