INDEX

Explanations

mentions of political entities or governmental organizations

oai_token-act-pair · gpt-3.5-turbo

references to the concept of a "state" in various contexts

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

aukee

-0.80

poons

-0.77

APR

-0.77

ritch

-0.76

CAST

-0.74

 batted

-0.73

 Hopkins

-0.68

 Masquerade

-0.68

poon

-0.67

endon

-0.66

POSITIVE LOGITS

rooms

0.86

lessness

0.83

SPONSORED

0.80

 capitals

0.74

less

0.72

wide

0.72

 apparatus

0.71

room

0.70

builders

0.69

 censor

0.68

Activations Density 0.057%

mentions of political entities or governmental organizations

references to the concept of a "state" in various contexts

No Comments

No Known Activations