INDEX

Explanations

references to specific names related to media or technology

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and locations

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

eers

-0.83

ilage

-0.80

 Purs

-0.73

eer

-0.72

escription

-0.71

 Bolshe

-0.69

lain

-0.68

trl

-0.68

İĭ

-0.67

£ı

-0.66

POSITIVE LOGITS

caster

0.82

axis

0.80

mington

0.75

endi

0.74

casting

0.70

vale

0.70

IELD

0.69

aii

0.69

 Rosenberg

0.66

PM

0.66

Activations Density 0.034%

references to specific names related to media or technology

proper nouns, particularly names and locations

No Comments

No Known Activations