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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 2457
    Prev
    Next
    INDEX
    Explanations

    language related to agreement for receiving communications and services

    oai_token-act-pair · gpt-3.5-turbo
    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
    abal
    -0.60
    ono
    -0.59
     Alph
    -0.59
     Grimoire
    -0.57
     Barber
    -0.54
     Shack
    -0.53
    osponsors
    -0.52
     Slot
    -0.52
     Âł Âł Âł Âł
    -0.52
     COUN
    -0.50
    POSITIVE LOGITS
    ").
    0.71
    .")
    0.67
    )."
    0.63
    ]);
    0.62
    asso
    0.61
     });
    0.58
    '."
    0.58
    ]."
    0.57
    ());
    0.57
    ë
    0.57
    Activations Density 0.058%

    No Known Activations