INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

names and terms related to people, places, and entities

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

 indo

-0.80

izable

-0.66

 Hercules

-0.66

 Olympia

-0.65

ļéĨĴ

-0.63

 Panther

-0.63

 Hoover

-0.62

PDATE

-0.62

 basketball

-0.60

 Lego

-0.60

POSITIVE LOGITS

avan

1.16

ttp

1.09

agh

0.98

ilipp

0.95

patrick

0.94

awan

0.93

awa

0.92

ythm

0.91

reement

0.90

awk

0.89

Activations Density 0.016%

names of individuals

names and terms related to people, places, and entities

No Comments

No Known Activations