© 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. 10-RES-JB
    11. 20416
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing intentions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    subjects and their actions or intentions related to communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obscurity
    -0.65
     Clever
    -0.64
    hovah
    -0.62
     Reporting
    -0.62
     newcom
    -0.60
    Translation
    -0.59
     Citation
    -0.58
     Pse
    -0.58
    cial
    -0.56
    YP
    -0.56
    POSITIVE LOGITS
     intends
    1.43
     regretted
    1.26
     intend
    1.25
     wants
    1.23
     would
    1.18
     wanted
    1.15
    'd
    1.14
     intention
    1.13
     expects
    1.13
    'll
    1.12
    Activations Density 0.278%

    No Known Activations