INDEX

Explanations

phrases indicating a sense of extremity or intensity

oai_token-act-pair · gpt-3.5-turbo

phrases indicating limits or extremes beyond normal bounds

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

si

-0.73

Ped

-0.70

ICAN

-0.68

hyde

-0.67

pmwiki

-0.66

cu

-0.64

vic

-0.63

nian

-0.63

 WATCHED

-0.63

male

-0.62

POSITIVE LOGITS

 comprehension

0.88

 bounds

0.83

 mere

0.80

 redemption

0.80

iche

0.79

 Borders

0.77

 infancy

0.75

 doubt

0.75

 reach

0.74

esis

0.74

Activations Density 0.035%

phrases indicating a sense of extremity or intensity

phrases indicating limits or extremes beyond normal bounds

No Comments

No Known Activations