INDEX

Explanations

specific references to the name "Durham"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Dur" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ħĭ

-0.84

 Simulator

-0.79

NetMessage

-0.77

Lens

-0.64

roads

-0.64

opsy

-0.64

 Ethics

-0.62

htaking

-0.61

 directors

-0.61

 Mara

-0.61

POSITIVE LOGITS

ably

1.10

ability

0.99

locks

0.96

ango

0.96

anty

0.94

abl

0.94

lock

0.94

abil

0.91

rell

0.90

ables

0.87

Activations Density 0.038%

specific references to the name "Durham"

occurrences of the word "Dur" in various contexts

No Comments

No Known Activations