INDEX

Explanations

mentions of the word "porridge"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "por" and its variations, likely indicating discussions related to a specific topic or person tied to that term

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

enegger

-0.82

ITNESS

-0.73

 GOODMAN

-0.73

EngineDebug

-0.70

DERR

-0.68

 sorts

-0.67

è£ħ

-0.66

OHN

-0.65

schild

-0.64

 Dickinson

-0.64

POSITIVE LOGITS

oshenko

1.20

cel

1.12

agraph

1.09

folios

1.06

cup

1.05

ters

1.04

bably

1.04

plet

1.03

por

0.98

quet

0.98

Activations Density 0.018%

mentions of the word "porridge"

occurrences of the word "por" and its variations, likely indicating discussions related to a specific topic or person tied to that term

No Comments

No Known Activations