INDEX

Explanations

words related to physically challenging or demanding activities

oai_token-act-pair · gpt-3.5-turbo

gerunds and present participles indicating ongoing actions

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

 Leilan

-0.84

 Atmosp

-0.75

 Liberties

-0.73

MAT

-0.70

ãĤ¼ãĤ¦ãĤ¹

-0.69

oresc

-0.67

itia

-0.66

 SERV

-0.65

MAT

-0.65

vironment

-0.65

POSITIVE LOGITS

puff

0.83

pole

0.80

strap

0.75

baugh

0.75

staking

0.74

ball

0.74

 prick

0.72

heed

0.72

chair

0.70

stone

0.70

Activations Density 0.164%

words related to physically challenging or demanding activities

gerunds and present participles indicating ongoing actions

No Comments

No Known Activations