INDEX

Explanations

information about a topic

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce additional information or detail

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

 Sabha

-0.85

externalActionCode

-0.76

rang

-0.75

OGR

-0.74

mouth

-0.73

gam

-0.73

itched

-0.69

 teasp

-0.68

KO

-0.68

iyah

-0.67

POSITIVE LOGITS

how

0.88

 whats

0.80

 topics

0.79

why

0.76

 yourself

0.69

 calib

0.69

 Yourself

0.65

 specifics

0.65

 details

0.64

EB

0.63

Activations Density 0.050%

information about a topic

phrases that introduce additional information or detail

No Comments

No Known Activations