INDEX

Explanations

mentions of foreign governmental officials

oai_token-act-pair · gpt-3.5-turbo

references to governmental foreign affairs

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

FUL

-0.79

CRIP

-0.71

oven

-0.70

XM

-0.69

orah

-0.69

 Ragnarok

-0.69

chens

-0.68

earable

-0.66

illation

-0.66

agically

-0.66

POSITIVE LOGITS

 Affairs

0.99

policy

0.89

 Relations

0.89

 affairs

0.87

 Fighters

0.81

 Policy

0.78

 relations

0.77

Aid

0.76

 nationals

0.76

 policy

0.74

Activations Density 0.014%

mentions of foreign governmental officials

references to governmental foreign affairs

No Comments

No Known Activations