INDEX

Explanations

references to a specific family or company name ("Koch")

oai_token-act-pair · gpt-3.5-turbo

mentions of the Koch brothers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ears

-0.68

country

-0.65

Condition

-0.65

reviewed

-0.64

General

-0.64

IENCE

-0.63

LEASE

-0.62

ience

-0.62

general

-0.62

OX

-0.61

POSITIVE LOGITS

 Koch

1.05

istani

0.95

ileaks

0.89

sburg

0.84

mere

0.84

anski

0.82

arov

0.82

liga

0.80

pins

0.79

alore

0.79

Activations Density 0.011%

references to a specific family or company name ("Koch")

mentions of the Koch brothers

No Comments

No Known Activations