INDEX

Explanations

phrases related to locations or names

oai_token-act-pair · gpt-3.5-turbo

specific sequences related to a particular name or term

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

 indo

-0.79

 Olympia

-0.68

 Hercules

-0.65

ļéĨĴ

-0.64

PDATE

-0.63

 psychiat

-0.63

 basketball

-0.63

 Curiosity

-0.62

 Gemini

-0.62

 Hoover

-0.62

POSITIVE LOGITS

ttp

1.17

avan

1.14

agh

1.06

allery

1.01

awa

0.97

ythm

0.95

orst

0.93

awan

0.92

awks

0.92

ilipp

0.91

Activations Density 0.009%

phrases related to locations or names

specific sequences related to a particular name or term

No Comments

No Known Activations