INDEX

Explanations

verbs related to mental activities like thinking, imagining, remembering, and understanding

oai_token-act-pair · gpt-3.5-turbo

expressions of thought and imagination

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

 bats

-0.65

 attacked

-0.64

 Gazette

-0.62

 defence

-0.61

 humanities

-0.61

Bok

-0.61

 Grimm

-0.61

 tresp

-0.60

 catapult

-0.60

 rover

-0.60

POSITIVE LOGITS

ħĭ

0.86

Ĳ

0.76

ĵĺ

0.75

ģĸ

0.75

enary

0.75

ĸ

0.74

athom

0.71

cue

0.71

qv

0.71

alogy

0.69

Activations Density 0.126%

verbs related to mental activities like thinking, imagining, remembering, and understanding

expressions of thought and imagination

No Comments

No Known Activations