INDEX

Explanations

some specific symbols and phrases that may not have a clear context from the given data

oai_token-act-pair · gpt-3.5-turbo

special characters and symbols in the text

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

sted

-0.66

wcs

-0.64

ramer

-0.62

 marqu

-0.62

onite

-0.61

 union

-0.61

TPPStreamerBot

-0.59

ement

-0.59

intern

-0.58

 grazing

-0.58

POSITIVE LOGITS

 Fiction

0.78

 Diseases

0.68

ORGE

0.67

 Proced

0.66

 Ibid

0.65

 Continued

0.64

 Cooldown

0.63

 Sheen

0.63

 Differences

0.63

 Subjects

0.63

Activations Density 0.156%

some specific symbols and phrases that may not have a clear context from the given data

special characters and symbols in the text

No Comments

No Known Activations