INDEX

Explanations

instances of the phrase "too much"

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize excessiveness or abundance

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

saf

-0.94

selves

-0.88

ologies

-0.87

byn

-0.86

stead

-0.84

ands

-0.83

inav

-0.82

iversary

-0.81

ĪĴ

-0.76

İĭ

-0.76

POSITIVE LOGITS

 emphasis

0.99

 attention

0.91

 firepower

0.85

 inconsistency

0.81

 temptation

0.80

 trouble

0.80

 effort

0.79

 negativity

0.78

 exposure

0.78

 time

0.78

Activations Density 0.036%

instances of the phrase "too much"

phrases that emphasize excessiveness or abundance

No Comments

No Known Activations