INDEX

Explanations

phrases indicating steps or actions required to achieve a specific goal

oai_token-act-pair · gpt-3.5-turbo

phrases indicating steps or instructions

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

bars

-0.64

 perished

-0.63

marine

-0.62

 tram

-0.60

 drip

-0.60

 diapers

-0.58

storms

-0.58

ingen

-0.58

 drowned

-0.58

sed

-0.58

POSITIVE LOGITS

 Activate

0.79

aucus

0.69

osi

0.66

igmat

0.64

 Racer

0.63

olean

0.62

ertain

0.61

 Apply

0.61

rely

0.61

 sshd

0.60

Activations Density 0.058%

phrases indicating steps or actions required to achieve a specific goal

phrases indicating steps or instructions

No Comments

No Known Activations