INDEX

Explanations

mentions of specific research institutions, particularly Scripps Research Institute

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "cripple" and its variations

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

 Antar

-0.81

isle

-0.66

izes

-0.65

ware

-0.65

izer

-0.62

 Laden

-0.62

 Corpus

-0.61

BW

-0.61

azar

-0.59

 Tripoli

-0.59

POSITIVE LOGITS

kefeller

0.95

erella

0.89

ulic

0.88

sburgh

0.79

nik

0.77

cens

0.75

eln

0.75

enthal

0.75

sylvania

0.75

mond

0.72

Activations Density 0.025%

mentions of specific research institutions, particularly Scripps Research Institute

mentions of the term "cripple" and its variations

No Comments

No Known Activations