Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 12414
    Prev
    Next
    INDEX
    Explanations

    the word "so" used in a consequential or explanatory context

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "and so" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hint
    -0.58
     Talking
    -0.57
    gie
    -0.56
     Depth
    -0.55
     Halls
    -0.55
     Liam
    -0.54
     tongue
    -0.54
     AAA
    -0.54
     vocals
    -0.53
     Crack
    -0.53
    POSITIVE LOGITS
    othe
    1.11
     forth
    1.10
    oths
    1.09
    apy
    1.06
    bered
    1.01
    othes
    1.00
    oner
    0.99
    oooo
    0.97
    ooo
    0.94
    arin
    0.90
    Activations Density 0.049%

    No Known Activations