INDEX

Explanations

references to the concept of 'freedom' or 'free' in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "free" in various contexts

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

 Takeru

-0.92

 sidx

-0.82

redients

-0.72

 Stories

-0.70

amel

-0.70

ENTS

-0.68

iosyn

-0.68

 therap

-0.65

emet

-0.65

iot

-0.64

POSITIVE LOGITS

bies

1.20

bie

1.07

 roam

0.98

 downloadable

0.82

boot

0.82

 federation

0.77

 download

0.75

form

0.75

 free

0.74

 eBook

0.73

Activations Density 0.021%

references to the concept of 'freedom' or 'free' in various contexts

references to the concept of "free" in various contexts

No Comments

No Known Activations