INDEX

Explanations

sentences indicating something is clearly understood or obvious

oai_token-act-pair · gpt-3.5-turbo

phrases indicating clarity or certainty

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

umbn

-0.78

avorite

-0.77

izons

-0.76

sembly

-0.71

pes

-0.70

otos

-0.68

unte

-0.68

aution

-0.66

©¶æ

-0.65

alez

-0.65

POSITIVE LOGITS

 enough

0.77

aneously

0.69

 Signs

0.68

 sailing

0.67

 signs

0.66

ances

0.66

($)

0.66

 that

0.66

footed

0.65

why

0.64

Activations Density 0.030%

sentences indicating something is clearly understood or obvious

phrases indicating clarity or certainty

No Comments

No Known Activations