INDEX

Explanations

names being mentioned

oai_token-act-pair · gpt-3.5-turbo

the phrase "said" in various contexts, indicating attributions of speech or statements made by individuals

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¦

-0.80

²¾

-0.79

aired

-0.76

à¼

-0.75

vent

-0.75

folios

-0.72

otin

-0.70

opard

-0.68

lymp

-0.67

Ø

-0.67

POSITIVE LOGITS

 analysts

0.98

 spokeswoman

0.93

 analyst

0.92

 spokesman

0.90

 sources

0.88

 organizers

0.78

KR

0.78

 officials

0.77

 Angela

0.76

 spokesperson

0.76

Activations Density 0.063%

names being mentioned

the phrase "said" in various contexts, indicating attributions of speech or statements made by individuals

No Comments

No Known Activations