INDEX

Explanations

specific mentions of the phrase "One."

oai_token-act-pair · gpt-3.5-turbo

references to the "One" brand or product

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ickr

-0.82

ruary

-0.75

rador

-0.75

lishes

-0.73

achusetts

-0.71

 externalToEVAOnly

-0.71

lished

-0.70

andum

-0.69

urat

-0.66

lishing

-0.65

POSITIVE LOGITS

 Hundred

1.08

xus

0.96

esan

0.91

 Direction

0.84

gger

0.81

 Thousand

0.77

hood

0.72

lihood

0.71

 hundred

0.71

 Million

0.71

Activations Density 0.048%

specific mentions of the phrase "One."

references to the "One" brand or product

No Comments

No Known Activations