INDEX

Explanations

specific terms related to medical procedures or conditions

oai_token-act-pair · gpt-3.5-turbo

words related to actions or processes in a legal or formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Marketable

-0.72

Proof

-0.66

 Jets

-0.66

fare

-0.62

fell

-0.62

 Wonderland

-0.62

 Silk

-0.61

 mileage

-0.60

Premium

-0.60

 Mankind

-0.60

POSITIVE LOGITS

Ã³n

1.39

aci

1.22

enda

1.12

Ã©e

1.01

oup

0.98

Ã©s

0.96

uations

0.95

encies

0.94

uca

0.94

iso

0.93

Activations Density 0.012%

specific terms related to medical procedures or conditions

words related to actions or processes in a legal or formal context

No Comments

No Known Activations