INDEX

Explanations

words related to powerful or impactful actions or events

oai_token-act-pair · gpt-3.5-turbo

occurrences of specific brands or notable figures related to events or themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

inous

-0.66

 helmets

-0.65

ãĥ³ãĤ¸

-0.64

 goggles

-0.63

 straps

-0.62

brand

-0.62

 abdom

-0.60

OAD

-0.59

 judgment

-0.59

attribute

-0.59

POSITIVE LOGITS

Pow

0.92

ciation

0.84

iary

0.82

itures

0.78

eful

0.77

holder

0.75

artz

0.75

Ã©t

0.75

ishers

0.74

iation

0.73

Activations Density 0.025%

words related to powerful or impactful actions or events

occurrences of specific brands or notable figures related to events or themes

No Comments

No Known Activations