INDEX

Explanations

phrases involving the word "many"

oai_token-act-pair · gpt-3.5-turbo

the repetition of the word "many" in various contexts

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

 appre

-0.63

ãĤ´

-0.62

 clay

-0.60

 appro

-0.59

ãĤ´ãĥ³

-0.58

 optics

-0.58

 assass

-0.58

 Bounty

-0.57

 grenade

-0.57

 GEAR

-0.56

POSITIVE LOGITS

doms

0.90

Downloadha

0.79

 albeit

0.78

bang

0.77

 besides

0.75

western

0.72

blooded

0.71

umeric

0.71

ideo

0.71

 sidx

0.71

Activations Density 0.355%

phrases involving the word "many"

the repetition of the word "many" in various contexts

No Comments

No Known Activations