INDEX

Explanations

references to physical locations or environments

oai_token-act-pair · gpt-3.5-turbo

terms associated with physical locations or environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nce

-0.68

 Recommend

-0.65

tein

-0.64

asus

-0.63

ERAL

-0.63

 citation

-0.63

CHAR

-0.62

ALLY

-0.61

Statement

-0.61

ANC

-0.60

POSITIVE LOGITS

creen

1.20

pring

1.15

cape

1.11

chool

1.09

mith

1.05

heet

1.00

paces

0.95

ystem

0.94

avers

0.94

itters

0.94

Activations Density 0.229%

references to physical locations or environments

terms associated with physical locations or environments

No Comments

No Known Activations