INDEX

Explanations

references to shredding or destroying something

oai_token-act-pair · gpt-3.5-turbo

the concept of "shredding" or breaking something into smaller pieces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

annis

-0.75

juven

-0.70

 Trop

-0.63

ague

-0.61

Ple

-0.61

Nex

-0.61

endment

-0.59

OPA

-0.58

 Crimes

-0.57

 Floor

-0.57

POSITIVE LOGITS

 shred

1.21

ding

1.09

itionally

1.02

sburg

0.88

sonian

0.87

der

0.86

aby

0.85

 tremend

0.84

ulously

0.84

itional

0.84

Activations Density 0.012%

references to shredding or destroying something

the concept of "shredding" or breaking something into smaller pieces

No Comments

No Known Activations