INDEX

Explanations

words related to legal actions, such as "appeal" and "ruling."

oai_token-act-pair · gpt-3.5-turbo

terms related to legal appeals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

kson

-0.78

fters

-0.66

ãĤ¿

-0.62

 Hots

-0.62

adata

-0.62

ifa

-0.60

FORE

-0.59

apy

-0.58

ipes

-0.58

shaw

-0.58

POSITIVE LOGITS

 against

0.89

 court

0.88

against

0.79

 tribunal

0.77

ĸļ

0.77

 appeals

0.75

process

0.72

 judge

0.71

 courts

0.71

rators

0.70

Activations Density 0.036%

words related to legal actions, such as "appeal" and "ruling."

terms related to legal appeals

No Comments

No Known Activations