INDEX

Explanations

words related to legal terms and offenses

oai_token-act-pair · gpt-3.5-turbo

references to criminal charges and legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nar

-0.67

 sonic

-0.59

 scrap

-0.57

 scorp

-0.57

wel

-0.57

 Weasley

-0.56

sy

-0.56

vre

-0.56

 spider

-0.55

pal

-0.55

POSITIVE LOGITS

?????-?????-

0.92

Same

0.85

ccording

0.84

Orderable

0.84

window

0.84

Repl

0.82

?????-

0.82

OVA

0.81

Located

0.80

Allows

0.80

Activations Density 0.149%

words related to legal terms and offenses

references to criminal charges and legal terminology

No Comments

No Known Activations