Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20179
    Prev
    Next
    INDEX
    Explanations

    comparisons between different entities or objects

    oai_token-act-pair · gpt-3.5-turbo

    connections and comparisons between various elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    everal
    -0.81
    ="/
    -0.69
    elsen
    -0.68
    eln
    -0.68
    idable
    -0.67
    ivities
    -0.66
    votes
    -0.65
    eport
    -0.65
    isco
    -0.64
    umbn
    -0.63
    POSITIVE LOGITS
     except
    1.79
    except
    1.33
     minus
    1.16
     albeit
    1.16
     although
    1.03
    Except
    1.02
     but
    0.98
     Except
    0.96
     though
    0.92
    minus
    0.92
    Activations Density 0.267%

    No Known Activations