INDEX

Explanations

phrases related to human rights

oai_token-act-pair · gpt-3.5-turbo

mentions of human rights and related issues

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

BALL

-0.82

 Claus

-0.80

ULAR

-0.76

STRUCT

-0.69

forth

-0.69

Arc

-0.68

raft

-0.64

ername

-0.63

ASH

-0.62

 Pound

-0.62

POSITIVE LOGITS

 abuses

1.07

 violations

1.06

 treaties

0.89

 activists

0.85

 activist

0.83

 enforcement

0.83

rights

0.82

 rights

0.82

 advocacy

0.81

 tribunal

0.81

Activations Density 0.027%

phrases related to human rights

mentions of human rights and related issues

No Known Activations