© 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. 2-RES-JB
    11. 9414
    Prev
    Next
    INDEX
    Explanations

    prepositions of place

    oai_token-act-pair · gpt-3.5-turbo

    the concept of origins or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hor
    -0.74
     neutron
    -0.74
     fodder
    -0.70
     che
    -0.69
     horizon
    -0.68
     chew
    -0.67
     pockets
    -0.66
    lette
    -0.64
     arsen
    -0.64
     spaghetti
    -0.64
    POSITIVE LOGITS
    }.
    0.72
    %).
    0.70
    Columb
    0.70
    OAD
    0.69
    Rev
    0.68
    ealous
    0.68
     Coliseum
    0.68
    Cause
    0.67
     Admission
    0.66
     Frazier
    0.65
    Activations Density 0.000%

    No Known Activations