INDEX

Explanations

mentions of political conflicts, military actions, and governmental terms

oai_token-act-pair · gpt-3.5-turbo

references to military actions and political unrest

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Oaks

-0.86

Cert

-0.79

mith

-0.77

borgh

-0.77

Premium

-0.77

 Whitney

-0.75

ertation

-0.75

CLA

-0.74

 Spielberg

-0.74

Factor

-0.73

POSITIVE LOGITS

 militias

1.22

 rebels

1.20

 separatists

1.19

 regime

1.17

 insurgents

1.17

 Houth

1.13

 separatist

1.12

 militants

1.11

 insurgency

1.10

 militia

1.09

Activations Density 0.923%

mentions of political conflicts, military actions, and governmental terms

references to military actions and political unrest

No Comments

No Known Activations