INDEX

Explanations

general concepts

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to general statements or observations about various topics

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

Future

-0.81

leted

-0.78

Fax

-0.78

Reb

-0.77

letes

-0.72

lyn

-0.69

Write

-0.67

RN

-0.66

Destroy

-0.65

Tomorrow

-0.65

POSITIVE LOGITS

 relativity

1.08

izations

0.95

 vicinity

0.82

ignment

0.80

arily

0.78

 anesthesia

0.76

ization

0.74

arial

0.74

 aviation

0.73

ado

0.71

Activations Density 0.014%

general concepts

phrases that refer to general statements or observations about various topics

No Comments

No Known Activations