INDEX

Explanations

proper nouns or phrases related to hidden or secret things

oai_token-act-pair · gpt-3.5-turbo

instances of the word "hidden" referring to concealed or obscured concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nia

-0.82

annis

-0.81

Pwr

-0.77

sburgh

-0.74

nan

-0.73

ctive

-0.73

alon

-0.73

umbn

-0.73

ucc

-0.72

adjusted

-0.71

POSITIVE LOGITS

 hidden

0.91

 Hidden

0.88

 recess

0.88

gem

0.84

 stash

0.82

 behind

0.81

 hatch

0.80

 treasure

0.79

 underground

0.78

 depths

0.78

Activations Density 0.014%

proper nouns or phrases related to hidden or secret things

instances of the word "hidden" referring to concealed or obscured concepts

No Comments

No Known Activations