© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 4370
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lack or absence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating inadequacy or something being less than expected

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.79
     [|
    -0.65
     Dickinson
    -0.59
    olds
    -0.58
    YN
    -0.57
     elders
    -0.56
     Pengu
    -0.56
     Sutherland
    -0.55
     Foley
    -0.55
    ||||
    -0.55
    POSITIVE LOGITS
    except
    0.86
     except
    0.85
     whatsoever
    0.82
     resembling
    0.81
    pires
    0.77
    ificant
    0.70
    Except
    0.69
    ¬¼
    0.68
     happening
    0.67
     transpired
    0.66
    Activations Density 0.192%

    No Known Activations