INDEX

Explanations

mentions of a specific person, 'L', with varying additional information

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'L' 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥĨãĤ£

-0.77

smanship

-0.70

hower

-0.69

 Subtle

-0.68

ãĤ¡

-0.68

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.66

 Primal

-0.65

rolet

-0.62

gerald

-0.62

 Prohibition

-0.61

POSITIVE LOGITS

ocker

1.20

ifestyle

1.16

adders

1.16

arger

1.14

ibrarian

1.13

ipp

1.10

ayers

1.10

aund

1.10

umber

1.09

ava

1.08

Activations Density 0.044%

mentions of a specific person, 'L', with varying additional information

occurrences of the letter 'L' in various contexts

No Comments

No Known Activations