INDEX

Explanations

names of managerial positions in various organizations

oai_token-act-pair · gpt-3.5-turbo

mentions of managerial roles or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

çīĪ

-0.84

ENC

-0.80

FER

-0.78

cale

-0.65

milo

-0.65

ilings

-0.63

lihood

-0.62

 prelim

-0.62

bent

-0.62

encing

-0.62

POSITIVE LOGITS

iewicz

0.80

ial

0.79

stadt

0.78

ials

0.75

anova

0.71

oeuv

0.70

eers

0.70

owitz

0.69

ihilation

0.69

iola

0.69

Activations Density 0.024%

names of managerial positions in various organizations

mentions of managerial roles or titles

No Comments

No Known Activations