INDEX

Explanations

mentions of managerial roles or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

-0.80

FER

-0.66

ENC

-0.66

--------------------------------------------------------

-0.62

milo

-0.62

MQ

-0.61

lihood

-0.60

READ

-0.60

DonaldTrump

-0.60

teenth

-0.59

POSITIVE LOGITS

ial

0.94

ials

0.88

ially

0.82

agers

0.77

urally

0.76

hips

0.75

icky

0.74

iewicz

0.74

rors

0.73

oeuv

0.72

Activations Density 0.032%

mentions of managerial roles or positions

No Comments

No Known Activations