INDEX

Explanations

proper nouns, particularly names like "Warren."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Warren."

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

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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dayName

-0.93

ãĤ´ãĥ³

-0.81

netflix

-0.80

pmwiki

-0.79

unal

-0.74

asus

-0.74

odic

-0.72

 conflic

-0.70

mble

-0.70

illin

-0.69

POSITIVE LOGITS

 Buffett

1.17

sburg

1.02

 Farrell

0.94

 Sapp

0.89

 Warren

0.86

rade

0.84

 Davidson

0.79

 Harding

0.77

ston

0.76

ers

0.76

Activations Density 0.034%

proper nouns, particularly names like "Warren."

mentions of the name "Warren."

No Comments

No Known Activations