INDEX

Explanations

comparisons or emphasis on level or quality

oai_token-act-pair · gpt-3.5-turbo

comparisons or phrases emphasizing that something is greater or more significant than another

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

 largeDownload

-0.76

CLASSIFIED

-0.69

ãģ®ç

-0.65

 Juda

-0.64

EMENT

-0.61

NEY

-0.60

 Direction

-0.60

ãĥ¡

-0.60

Winged

-0.59

ilic

-0.59

POSITIVE LOGITS

whelming

0.81

atos

0.76

 usual

0.72

vol

0.67

atever

0.67

usercontent

0.66

etheless

0.65

contact

0.64

represent

0.63

rel

0.62

Activations Density 0.087%

comparisons or emphasis on level or quality

comparisons or phrases emphasizing that something is greater or more significant than another

No Comments

No Known Activations