INDEX

Explanations

The neuron is focusing on location-based information

oai_token-act-pair · gpt-3.5-turbo

instances of questions and inquiries

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

zbollah

-0.69

 Zoro

-0.63

 occult

-0.62

Mao

-0.60

etheless

-0.60

Neo

-0.60

isoft

-0.59

EVE

-0.59

 Manson

-0.59

 princip

-0.58

POSITIVE LOGITS

 Retrieved

1.04

(@

0.84

 Explain

0.84

Answer

0.81

?,

0.80

Read

0.77

='

0.74

Report

0.74

>:

0.73

0.72

Activations Density 0.735%

The neuron is focusing on location-based information

instances of questions and inquiries

No Comments

No Known Activations