INDEX

Explanations

phrases or symbols conveying specialized instructions or actions

oai_token-act-pair · gpt-3.5-turbo

specific symbols, potentially indicating formatting or coding elements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ysis

-0.79

zzle

-0.76

 Berm

-0.70

ppe

-0.69

Blu

-0.69

zzy

-0.66

 Borg

-0.65

 parted

-0.65

 limp

-0.64

iple

-0.64

POSITIVE LOGITS

cases

0.94

specific

0.90

0.86

stories

0.85

coll

0.85

micro

0.83

double

0.80

these

0.80

––

0.79

style

0.77

Activations Density 0.025%

phrases or symbols conveying specialized instructions or actions

specific symbols, potentially indicating formatting or coding elements

No Comments

No Known Activations