INDEX

Explanations

phrases related to comparisons and progress

oai_token-act-pair · gpt-3.5-turbo

comparative statements about levels or degrees of various factors

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

«ĺ

-0.79

hof

-0.78

İĭ

-0.78

ãĤ´ãĥ³

-0.75

ĳå£«

-0.74

imilar

-0.73

¤

-0.73

aldehyde

-0.71

è£

-0.69

¬¼

-0.69

POSITIVE LOGITS

than

0.85

 than

0.79

 rede

0.76

 absorb

0.73

 absorbed

0.72

 vested

0.69

 Metatron

0.68

 enrol

0.68

 repet

0.67

 absorbs

0.67

Activations Density 0.088%

phrases related to comparisons and progress

comparative statements about levels or degrees of various factors

No Comments

No Known Activations