© 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. 13517
    Prev
    Next
    INDEX
    Explanations

    information related to projects and productions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal involvement and collaboration in creative processes

    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
    carry
    -0.79
    SPONSORED
    -0.75
    alia
    -0.69
     mug
    -0.67
    ratom
    -0.67
    aunts
    -0.67
    Liber
    -0.66
    à
    -0.66
    emic
    -0.65
    overe
    -0.65
    POSITIVE LOGITS
     brainstorm
    1.13
     studio
    1.13
     designing
    1.09
     inspir
    1.05
     designers
    1.05
     screenplay
    0.98
     directors
    0.98
     collaborating
    0.97
     Studios
    0.95
     Studio
    0.95
    Activations Density 1.903%

    No Known Activations