INDEX

Explanations

phrases that reference locations or regions

oai_token-act-pair · gpt-3.5-turbo

the repetition of the word "around" 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 @ 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

xual

-0.79

inen

-0.77

nis

-0.68

oly

-0.66

ocy

-0.66

qua

-0.65

HO

-0.62

 istg

-0.61

ysis

-0.61

 gard

-0.60

POSITIVE LOGITS

 corners

0.87

clock

0.84

eatures

0.83

abouts

0.80

perty

0.72

lasses

0.69

 intersections

0.66

lihood

0.65

atform

0.64

ingu

0.62

Activations Density 0.041%

phrases that reference locations or regions

the repetition of the word "around" in various contexts

No Comments

No Known Activations