© 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. 11-RES-JB
    11. 7118
    Prev
    Next
    INDEX
    Explanations

    movie or album titles that contain special characters like âĢ

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nown
    -0.67
    ifications
    -0.64
     interf
    -0.64
     infringing
    -0.64
     administr
    -0.61
     lying
    -0.60
     Berm
    -0.60
     photoc
    -0.58
     unidentified
    -0.58
     obstruct
    -0.58
    POSITIVE LOGITS
    ı
    1.23
    ´
    1.22
    ĺ
    1.20
    Ĺ
    1.18
    ¬
    1.18
    Ħ¢
    1.13
    Ĵ
    1.12
    ª
    1.12
    į
    1.11
    §
    1.10
    Activations Density 0.230%

    No Known Activations