INDEX

Explanations

actions or recommendations related to making decisions or taking action

oai_token-act-pair · gpt-3.5-turbo

suggestions or recommendations for actions

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

ELD

-0.75

indle

-0.64

 cartoon

-0.60

 Fundamental

-0.60

 supposedly

-0.59

 tricked

-0.57

 morphed

-0.57

 wheelchair

-0.57

 rendered

-0.57

Radio

-0.57

POSITIVE LOGITS

 caution

0.84

 heed

0.81

 consult

0.81

 Recommend

0.80

 Helpful

0.80

 consider

0.80

geist

0.77

 beware

0.77

 hesitate

0.73

hement

0.71

Activations Density 0.346%

actions or recommendations related to making decisions or taking action

suggestions or recommendations for actions

No Comments

No Known Activations