INDEX

Explanations

instances of the word "relative" occurring in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms associated with comparisons or ratios

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

spr

-0.91

enegger

-0.87

ERG

-0.84

storm

-0.83

schild

-0.81

eret

-0.76

inis

-0.74

Ì¶

-0.73

iere

-0.72

alos

-0.72

POSITIVE LOGITS

 humidity

1.07

 ease

0.87

 pronoun

0.84

 newcomer

0.83

 pronouns

0.79

 importance

0.78

 autonomy

0.78

 obscurity

0.77

 anonymity

0.76

 easing

0.75

Activations Density 0.023%

instances of the word "relative" occurring in various contexts

terms associated with comparisons or ratios

No Comments

No Known Activations