© 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. 14121
    Prev
    Next
    INDEX
    Explanations

    phrases related to different aspects of a complex system or process

    oai_token-act-pair · gpt-3.5-turbo

    elements related to transactions and interactions within systems

    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
    addon
    -0.85
    ECA
    -0.76
    senal
    -0.73
    ahime
    -0.69
    +.
    -0.63
    luaj
    -0.60
    soType
    -0.59
    ?????-
    -0.57
     sqor
    -0.56
    ï¸
    -0.56
    POSITIVE LOGITS
     occurs
    1.25
     becomes
    1.21
     happens
    1.18
     goes
    1.18
     involves
    1.17
     gets
    1.16
     lasts
    1.15
     evolves
    1.14
     belongs
    1.13
     must
    1.12
    Activations Density 0.380%

    No Known Activations