INDEX

Explanations

mentions of news agency names

oai_token-act-pair · gpt-3.5-turbo

the presence of the term "REUTERS" in various contexts related to news reporting dates and locations

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

izers

-0.64

 Kardash

-0.61

uster

-0.61

Ö¼

-0.59

sed

-0.59

 Britann

-0.58

ysis

-0.58

naires

-0.58

 joints

-0.57

 beds

-0.56

POSITIVE LOGITS

CLASSIFIED

0.94

UTERS

0.93

FORE

0.88

photo

0.85

 REUTERS

0.85

AMI

0.83

allery

0.82

WARD

0.82

Film

0.79

externalActionCode

0.79

Activations Density 0.017%

mentions of news agency names

the presence of the term "REUTERS" in various contexts related to news reporting dates and locations

No Comments

No Known Activations