© 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. 18767
    Prev
    Next
    INDEX
    Explanations

    phrases related to activities or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of clause structures with a focus on providing specific information or reports

    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
    itol
    -0.69
     è£ıè
    -0.63
    conom
    -0.58
    ©¶æ
    -0.57
    ocl
    -0.55
    ira
    -0.55
    vez
    -0.55
    zb
    -0.54
    ĨĴ
    -0.53
    iple
    -0.53
    POSITIVE LOGITS
     respectively
    1.68
     etc
    1.00
    etc
    0.95
     whichever
    0.88
    depending
    0.86
     culminating
    0.80
     albeit
    0.79
     including
    0.78
     according
    0.77
     Leilan
    0.75
    Activations Density 0.545%

    No Known Activations