INDEX

Explanations

action words in imperative or declarative statements

oai_token-act-pair · gpt-3.5-turbo

statements regarding intentions, ideas, or plans

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

iates

-0.94

 pains

-0.67

Ago

-0.65

 interven

-0.65

iate

-0.65

eor

-0.64

iating

-0.63

 sides

-0.61

idences

-0.61

hens

-0.61

POSITIVE LOGITS

 moot

0.81

0.80

olate

0.74

 straightforward

0.72

 spelled

0.72

 based

0.70

 priceless

0.70

 probably

0.69

 definitely

0.69

 undoubtedly

0.69

Activations Density 0.196%

action words in imperative or declarative statements

statements regarding intentions, ideas, or plans

No Comments

No Known Activations