INDEX

Explanations

words related to surprising or sensational information

oai_token-act-pair · gpt-3.5-turbo

instances of the word 'shocking' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

xia

-0.95

©¶æ

-0.91

amins

-0.85

arten

-0.83

haps

-0.82

ophers

-0.82

ello

-0.80

folios

-0.78

oyal

-0.78

emis

-0.77

POSITIVE LOGITS

 Revelations

0.92

 revelations

0.79

aneously

0.79

LY

0.77

 revelation

0.75

ly

0.73

IFT

0.71

 Squid

0.71

ORN

0.69

 naked

0.68

Activations Density 0.020%

words related to surprising or sensational information

instances of the word 'shocking' in various contexts

No Comments

No Known Activations