INDEX

Explanations

instances of emphasis or particularly dominant words

oai_token-act-pair · gpt-3.5-turbo

instances of the word "much" to indicate a significant quantity or intensity 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pherd

-0.82

ħĭ

-0.77

grad

-0.77

saf

-0.76

Ń·

-0.73

İĭ

-0.72

ĪĴ

-0.70

²¾

-0.70

Enlarge

-0.70

selves

-0.69

POSITIVE LOGITS

NESS

0.78

 firepower

0.78

dmg

0.77

 hype

0.72

 effort

0.71

 emotion

0.71

fun

0.70

 detail

0.70

 bang

0.69

 integrity

0.69

Activations Density 0.038%

instances of emphasis or particularly dominant words

instances of the word "much" to indicate a significant quantity or intensity in various contexts

No Comments

No Known Activations