INDEX

Explanations

the word "that" as part of a phrase

oai_token-act-pair · gpt-3.5-turbo

the phrase "Now that," indicating a transition or a condition

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

tnc

-0.81

ARI

-0.66

Merit

-0.65

ONT

-0.65

DD

-0.65

ãĥĳ

-0.64

ãĥĺ

-0.63

ORPG

-0.63

 dstg

-0.62

agi

-0.61

POSITIVE LOGITS

 settles

0.78

acqu

0.74

 resolves

0.73

 pesky

0.72

hew

0.71

rely

0.71

 fateful

0.70

birth

0.69

 happens

0.68

 bitten

0.65

Activations Density 0.057%

the word "that" as part of a phrase

the phrase "Now that," indicating a transition or a condition

No Comments

No Known Activations