© 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. 11-RES-JB
    11. 18840
    Prev
    Next
    INDEX
    Explanations

    descriptions of properties or actions followed by a contrasting statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "also" indicating an additional point or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASE
    -0.69
    tten
    -0.68
    adal
    -0.66
    otiation
    -0.65
     meanwhile
    -0.64
    eting
    -0.63
    maxwell
    -0.63
    orum
    -0.62
    ukemia
    -0.61
     Ange
    -0.61
    POSITIVE LOGITS
     happens
    0.85
     includes
    0.84
     include
    0.79
     occasionally
    0.78
     included
    0.76
     incidentally
    0.76
     contains
    0.72
     optionally
    0.71
     indirectly
    0.70
     happen
    0.70
    Activations Density 0.132%

    No Known Activations