INDEX

Explanations

proper nouns related to a specific individual named "Davis."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Davis."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥĥãĥĪ

-0.76

emort

-0.68

isites

-0.68

liest

-0.67

ilater

-0.66

ugal

-0.66

 Seym

-0.65

bably

-0.65

 stranger

-0.65

folio

-0.64

POSITIVE LOGITS

 Davis

0.92

 Hanson

0.85

essa

0.80

Davis

0.78

eland

0.75

acre

0.74

ville

0.73

 Webb

0.72

ragon

0.72

âĸĳâĸĳ

0.69

Activations Density 0.017%

proper nouns related to a specific individual named "Davis."

mentions of the name "Davis."

No Comments

No Known Activations