© 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. 8-RES-JB
    11. 4592
    Prev
    Next
    INDEX
    Explanations

    phrases related to rankings or comparisons in size, performance, or other metrics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference rankings or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realised
    -0.73
    issance
    -0.65
     Leilan
    -0.65
     Nou
    -0.65
    riter
    -0.64
     corpus
    -0.64
     realise
    -0.64
     attendant
    -0.63
    ciation
    -0.61
     sensed
    -0.60
    POSITIVE LOGITS
    payers
    0.81
     prominently
    0.79
    Runner
    0.73
     favorably
    0.70
    aeper
    0.70
    among
    0.70
    vantage
    0.69
    ophon
    0.68
    âĺħâĺħ
    0.68
    Ranked
    0.68
    Activations Density 0.076%

    No Known Activations