INDEX

Explanations

phrases related to processes or methods

oai_token-act-pair · gpt-3.5-turbo

phrases describing processes or methods

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

ibrary

-0.80

lux

-0.73

lvl

-0.70

dq

-0.62

 McKenna

-0.59

Week

-0.59

lux

-0.58

ournal

-0.58

 Invention

-0.58

Day

-0.57

POSITIVE LOGITS

otto

0.66

rez

0.65

icans

0.62

atown

0.62

soType

0.61

 interpreting

0.61

itives

0.61

ortium

0.61

 conduit

0.61

TRY

0.60

Activations Density 0.155%

phrases related to processes or methods

phrases describing processes or methods

No Comments

No Known Activations