INDEX

Explanations

the word "Brock" followed by a single-digit or double-digit number

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Brock."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

udic

-0.71

ffic

-0.70

circ

-0.68

 conspicuous

-0.67

MX

-0.62

pmwiki

-0.61

minist

-0.61

exec

-0.61

 relativity

-0.60

pron

-0.60

POSITIVE LOGITS

 Brock

1.22

lings

0.91

storms

0.84

bags

0.81

fall

0.80

 Upton

0.80

leys

0.80

mire

0.79

hurst

0.79

 Wyatt

0.79

Activations Density 0.007%

the word "Brock" followed by a single-digit or double-digit number

mentions of the name "Brock."

No Comments

No Known Activations