INDEX

Explanations

language related to political policies

oai_token-act-pair · gpt-3.5-turbo

phrases related to governmental policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

issan

-0.82

ITNESS

-0.79

amina

-0.75

lighting

-0.74

theless

-0.73

athan

-0.72

avez

-0.70

ruciating

-0.69

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.68

amaz

-0.68

POSITIVE LOGITS

 policies

1.02

 prescriptions

0.91

 policy

0.82

aroo

0.80

 Policies

0.79

 enacted

0.79

olicy

0.79

 preferences

0.78

 stances

0.76

 choices

0.74

Activations Density 0.019%

language related to political policies

phrases related to governmental policies

No Comments

No Known Activations