INDEX

Explanations

references to specific named entities, particularly those starting with the letter N and followed by a single-digit number

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "N"

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

 Gibraltar

-0.72

espie

-0.65

 Cerberus

-0.64

 highs

-0.64

 Sparrow

-0.63

 breeze

-0.63

 unsupported

-0.62

 Izan

-0.62

gerald

-0.61

 Quartz

-0.61

POSITIVE LOGITS

aughty

1.20

usra

1.19

anny

1.16

onsense

1.15

ucle

1.14

SS

1.08

ihil

1.08

omin

1.07

erv

1.06

igg

1.06

Activations Density 0.042%

references to specific named entities, particularly those starting with the letter N and followed by a single-digit number

occurrences of the letter "N"

No Comments

No Known Activations