INDEX

Explanations

references to historical events or time periods

oai_token-act-pair · gpt-3.5-turbo

specific years, particularly those in the 1920s

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

anamo

-0.73

ramer

-0.72

ioned

-0.71

ledged

-0.71

holder

-0.70

parency

-0.70

imon

-0.70

iaries

-0.69

amin

-0.69

RAM

-0.69

POSITIVE LOGITS

Osw

0.79

0.78

0.73

âĢķ

0.67

0.66

0.65

é¾įå¥ĳå£«

0.65

0.64

Activations Density 0.026%

references to historical events or time periods

specific years, particularly those in the 1920s

No Comments

No Known Activations