INDEX

Explanations

legal and judicial terms

oai_token-act-pair · gpt-3.5-turbo

references to legal actions or investigations related to governmental agencies

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

ãĤ¨ãĥ«

-1.06

Í

-0.94

ãĥŁ

-0.88

iour

-0.86

ãĥĺ

-0.85

reci

-0.84

 à¨

-0.82

ãĥİ

-0.78

ãĤ¤

-0.77

Ïī

-0.77

POSITIVE LOGITS

 Judicial

1.66

DOJ

1.65

 FOIA

1.64

 congressional

1.56

 subpoen

1.50

 Holder

1.41

 Congressional

1.41

 Grassley

1.39

 Attorney

1.39

 ACLU

1.38

Activations Density 0.495%

legal and judicial terms

references to legal actions or investigations related to governmental agencies

No Comments

No Known Activations