INDEX

Explanations

mentions of specific organizations or individuals, particularly related to politics or business

oai_token-act-pair · gpt-3.5-turbo

references to arguments or discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

FORMATION

-0.87

lihood

-0.75

mission

-0.68

missions

-0.66

ned

-0.66

DAY

-0.65

soever

-0.65

fulness

-0.64

 spaced

-0.64

âĸ¬

-0.64

POSITIVE LOGITS

uably

1.34

uments

1.13

raph

1.02

emouth

0.99

irl

0.95

roup

0.95

naire

0.91

ues

0.90

ansas

0.90

allery

0.89

Activations Density 0.036%

mentions of specific organizations or individuals, particularly related to politics or business

references to arguments or discussions

No Comments

No Known Activations