© 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. 6-RES-JB
    11. 838
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or processes being performed or achieved

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "through" 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
    ids
    -0.76
    abet
    -0.72
    ailable
    -0.71
    juven
    -0.65
    imens
    -0.63
    igh
    -0.63
    ouse
    -0.63
    \/
    -0.63
    CTV
    -0.62
    oom
    -0.62
    POSITIVE LOGITS
     intermedi
    0.96
     sheer
    0.76
     attrition
    0.75
     multiple
    0.69
     repetition
    0.68
     taxation
    0.68
     various
    0.67
     2021
    0.66
     inaction
    0.65
    lining
    0.65
    Activations Density 0.045%

    No Known Activations