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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 6829
    Prev
    Next
    INDEX
    Explanations

    places or positions within a certain context

    oai_token-act-pair · gpt-3.5-turbo
    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
    ivas
    -0.68
    put
    -0.64
    irs
    -0.62
     Glac
    -0.60
     Abilities
    -0.60
    het
    -0.60
    Constructed
    -0.60
    doi
    -0.58
    erial
    -0.57
    Graphics
    -0.57
    POSITIVE LOGITS
     slightest
    0.84
     deadline
    0.81
    chance
    0.76
    actively
    0.75
     earnest
    0.74
    erity
    0.74
    instead
    0.71
     mistake
    0.71
     sooner
    0.69
     desired
    0.68
    Activations Density 0.554%

    No Known Activations