INDEX

Explanations

references to a specific name or term ("Mic") and related words

oai_token-act-pair · gpt-3.5-turbo

references to microphones or similar audio equipment

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IVES

-0.70

mberg

-0.68

 Dull

-0.67

 Madison

-0.64

ACTED

-0.63

 Unified

-0.62

âĢİ

-0.62

 Tend

-0.61

witz

-0.61

ENGTH

-0.61

POSITIVE LOGITS

roman

1.45

helle

1.37

ropolitan

1.31

rones

1.30

rom

1.24

ror

1.19

HAEL

1.17

ron

1.16

onductor

1.15

rons

1.09

Activations Density 0.035%

references to a specific name or term ("Mic") and related words

references to microphones or similar audio equipment

No Comments

No Known Activations