INDEX

Explanations

performers and professionals in various industries

oai_token-act-pair · gpt-3.5-turbo

terms related to performers and professionals in the entertainment industry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

illance

-0.75

OLOG

-0.68

OLOGY

-0.68

States

-0.66

izontal

-0.66

ologic

-0.65

sole

-0.65

ovo

-0.65

arest

-0.64

rection

-0.64

POSITIVE LOGITS

hip

1.19

hips

1.17

 Jonah

1.09

 Joel

1.08

 David

1.08

 Cheryl

1.07

 John

1.05

 Greg

1.04

 Matthew

1.04

 Quentin

1.04

Activations Density 0.333%

performers and professionals in various industries

terms related to performers and professionals in the entertainment industry

No Comments

No Known Activations