INDEX

Explanations

terms related to electrical or electronic components or processes

oai_token-act-pair · gpt-3.5-turbo

variations of the word "elect" or related terms in different contexts

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

Lens

-0.71

iday

-0.70

acca

-0.67

^^^^

-0.66

WT

-0.65

ACK

-0.64

OAD

-0.64

ãĤ¬

-0.63

 Burk

-0.63

 Loft

-0.61

POSITIVE LOGITS

rification

1.23

ron

1.19

rics

1.17

rons

1.16

rified

1.16

roc

1.12

rical

1.12

ronic

1.08

rated

1.05

rum

1.03

Activations Density 0.017%

terms related to electrical or electronic components or processes

variations of the word "elect" or related terms in different contexts

No Comments

No Known Activations