INDEX

Explanations

words related to surprising or shocking events

oai_token-act-pair · gpt-3.5-turbo

references to shock and its effects

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

uties

-0.72

allery

-0.71

amins

-0.71

ickr

-0.71

umbers

-0.66

atively

-0.64

 arrang

-0.63

 misunder

-0.62

ately

-0.62

oreal

-0.60

POSITIVE LOGITS

wave

1.22

waves

1.19

 absor

1.09

ingly

0.93

tro

0.92

er

0.90

crow

0.86

imaru

0.81

pson

0.77

mong

0.76

Activations Density 0.033%

words related to surprising or shocking events

references to shock and its effects

No Comments

No Known Activations