© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 21398
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons of quantity or quality between different conditions or situations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to various economic and performance metrics

    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
     Gleaming
    -0.75
    eday
    -0.70
    wered
    -0.70
    adder
    -0.67
    iseum
    -0.65
    andise
    -0.63
    ADRA
    -0.62
    oplan
    -0.61
    apult
    -0.59
    Rule
    -0.59
    POSITIVE LOGITS
     altogether
    1.02
     (<
    0.94
     anymore
    0.94
     nor
    0.83
     bother
    0.73
     than
    0.71
    luster
    0.70
    yet
    0.70
     whatsoever
    0.69
     footprint
    0.69
    Activations Density 0.278%

    No Known Activations