INDEX

Explanations

the word "one" appearing in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to the number "one" 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

lished

-0.91

ickr

-0.79

 actionGroup

-0.77

ournal

-0.76

rawler

-0.76

lishes

-0.75

rador

-0.74

mingham

-0.74

ruary

-0.73

achusetts

-0.72

POSITIVE LOGITS

gger

1.05

lihood

0.92

xus

0.88

 Tone

0.85

cker

0.81

xit

0.81

lli

0.79

llo

0.78

cone

0.78

esan

0.78

Activations Density 0.027%

the word "one" appearing in various contexts

references to the number "one" in various contexts

No Comments

No Known Activations