© 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. 13376
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to reasons or causes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "because" indicating causal relationships

    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
    mint
    -0.74
    wn
    -0.71
    yan
    -0.71
    Gas
    -0.70
    alin
    -0.70
    agin
    -0.69
    lem
    -0.69
    ries
    -0.67
    ymph
    -0.66
    âĤ¬
    -0.65
    POSITIVE LOGITS
     they
    0.86
    */(
    0.79
    ecause
    0.69
     otherwise
    0.67
     someone
    0.67
     THEY
    0.66
    akening
    0.65
    ority
    0.65
     mistakenly
    0.64
     there
    0.64
    Activations Density 0.080%

    No Known Activations