INDEX

Explanations

items related to physical actions

oai_token-act-pair · gpt-3.5-turbo

words related to action and physical activities

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

emort

-0.73

SEA

-0.69

©¶æ¥µ

-0.65

¿½

-0.64

Definition

-0.63

ulative

-0.62

£ı

-0.61

 millenn

-0.59

secondary

-0.58

Specific

-0.58

POSITIVE LOGITS

 extraord

0.73

coon

0.70

antly

0.68

 fest

0.67

dab

0.64

uits

0.63

hers

0.63

itaire

0.63

lehem

0.62

worm

0.61

Activations Density 0.662%

items related to physical actions

words related to action and physical activities

No Comments

No Known Activations