INDEX

Explanations

mentions of armed forces and related activities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "armed."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rx

-0.88

HUD

-0.79

 Remastered

-0.74

acent

-0.72

article

-0.70

redo

-0.69

è£ħ

-0.69

Ĥİ

-0.67

orb

-0.65

algia

-0.65

POSITIVE LOGITS

 robbery

1.00

 insurrection

0.90

 robberies

0.87

 conflict

0.83

 Forces

0.80

 takeover

0.78

 robber

0.76

 robbers

0.76

 conflicts

0.76

iterranean

0.76

Activations Density 0.031%

mentions of armed forces and related activities

occurrences of the term "armed."

No Comments

No Known Activations