INDEX

Explanations

statements about comparisons or evaluations

oai_token-act-pair · gpt-3.5-turbo

strategies or claims about effectiveness in addressing significant issues

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 IMAGES

-0.70

 Units

-0.70

 Pieces

-0.65

axis

-0.62

 flyers

-0.62

 Attend

-0.61

 Unit

-0.60

 Surveillance

-0.60

 Davies

-0.59

 Recreation

-0.59

POSITIVE LOGITS

nor

0.84

elo

0.78

adish

0.72

TPPStreamerBot

0.70

esides

0.69

paralle

0.69

velt

0.68

omever

0.67

itent

0.66

onite

0.66

Activations Density 0.602%

statements about comparisons or evaluations

strategies or claims about effectiveness in addressing significant issues

No Comments

No Known Activations