INDEX

Explanations

mention of photographs or images

oai_token-act-pair · gpt-3.5-turbo

references to media, particularly photos and rankings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

PsyNetMessage

-0.66

weak

-0.63

coni

-0.62

Friend

-0.62

ingham

-0.58

ounded

-0.56

rost

-0.55

rities

-0.55

Love

-0.55

igham

-0.54

POSITIVE LOGITS

 earners

0.74

 contender

0.68

 swoop

0.68

venture

0.67

nings

0.66

acher

0.66

dl

0.62

yip

0.62

Hai

0.62

 pyramid

0.62

Activations Density 0.158%

mention of photographs or images

references to media, particularly photos and rankings

No Comments

No Known Activations