© 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. 9-RES-JB
    11. 1865
    Prev
    Next
    INDEX
    Explanations

    adjectives related to evaluating traits or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    expressions that indicate a lack of value or merit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.85
    hn
    -0.64
    inence
    -0.63
     [|
    -0.60
    YN
    -0.60
    hma
    -0.59
    clerosis
    -0.59
    majority
    -0.58
    ospons
    -0.58
    bach
    -0.58
    POSITIVE LOGITS
    except
    0.96
     whatsoever
    0.93
     except
    0.92
    nor
    0.84
     nor
    0.83
    soever
    0.81
     besides
    0.80
     resembling
    0.78
     Croat
    0.66
     separates
    0.65
    Activations Density 0.224%

    No Known Activations