INDEX

Explanations

sentences where the word "puppets" or variations of it are mentioned

oai_token-act-pair · gpt-3.5-turbo

references to "Muppets" and related characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

UTION

-0.69

GW

-0.67

UTE

-0.67

-0.65

 dissolution

-0.65

DOM

-0.63

Textures

-0.62

 shame

-0.62

AMS

-0.61

Charges

-0.61

POSITIVE LOGITS

enhagen

1.20

upp

1.16

olicy

1.09

sburgh

1.08

ortun

0.99

etry

0.94

enthal

0.91

isine

0.89

ledged

0.87

elf

0.85

Activations Density 0.007%

sentences where the word "puppets" or variations of it are mentioned

references to "Muppets" and related characters

No Comments

No Known Activations