INDEX

Explanations

points of interest or focus within larger groups or categories

oai_token-act-pair · gpt-3.5-turbo

phrases that express a quantity or proportion related to a subject

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

afia

-0.70

RAW

-0.61

ovember

-0.61

rets

-0.60

 misunderstand

-0.59

 rematch

-0.57

 redesign

-0.57

IFF

-0.57

 allot

-0.57

Picture

-0.57

POSITIVE LOGITS

 whom

0.96

arching

0.77

 course

0.75

 theirs

0.73

etheless

0.70

 which

0.67

 them

0.65

course

0.64

 yours

0.63

ãĥ´

0.62

Activations Density 0.089%

points of interest or focus within larger groups or categories

phrases that express a quantity or proportion related to a subject

No Comments

No Known Activations