© 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. 6467
    Prev
    Next
    INDEX
    Explanations

    phrases related to cause and effect

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or outcomes related to various issues

    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
    Mos
    -0.69
    itsch
    -0.66
    soon
    -0.65
    Steel
    -0.64
    tel
    -0.64
    did
    -0.64
    hatt
    -0.64
    tw
    -0.63
    founded
    -0.63
    she
    -0.63
    POSITIVE LOGITS
     greater
    0.85
     gradual
    0.84
     increased
    0.80
     higher
    0.79
     considerable
    0.79
     continual
    0.78
     stagnation
    0.76
     decreased
    0.76
     unwanted
    0.75
     significant
    0.74
    Activations Density 0.229%

    No Known Activations