INDEX

Explanations

mentions of locations where the speaker lives

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "living in"

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

killed

-0.82

casters

-0.75

¿½

-0.74

Ĳ

-0.74

catentry

-0.72

 undone

-0.69

 Presbyter

-0.65

awa

-0.65

ector

-0.65

offer

-0.64

POSITIVE LOGITS

 accordance

1.04

ordinate

0.94

 Denmark

0.85

 France

0.85

clud

0.82

egal

0.80

 spite

0.80

0.79

 England

0.78

 lieu

0.76

Activations Density 0.078%

mentions of locations where the speaker lives

instances of the phrase "living in"

No Comments

No Known Activations