INDEX

Explanations

phrases or sentences where the concept of something becoming more intense, complicated, or worsening is described

oai_token-act-pair · gpt-3.5-turbo

phrases indicating increasing complexity or complication in situations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

amiya

-0.71

velt

-0.68

 Britann

-0.63

orney

-0.61

 Archdemon

-0.60

 caution

-0.59

arta

-0.57

 Tanz

-0.56

 Principle

-0.56

athing

-0.56

POSITIVE LOGITS

rid

1.01

cloneembedreportprint

0.94

TING

0.81

 underway

0.80

tin

0.80

 progressively

0.78

ģĸ

0.75

ITS

0.74

uters

0.72

tails

0.71

Activations Density 0.074%

phrases or sentences where the concept of something becoming more intense, complicated, or worsening is described

phrases indicating increasing complexity or complication in situations

No Comments

No Known Activations