INDEX

Explanations

words related to walls

oai_token-act-pair · gpt-3.5-turbo

references to walls and barriers

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

IFrame

Link

Negative Logits

Gene

-0.84

Eug

-0.68

phrine

-0.67

 delegated

-0.66

Pacific

-0.66

lihood

-0.66

ensation

-0.63

ptive

-0.61

Wild

-0.60

orean

-0.60

POSITIVE LOGITS

papers

1.24

abies

1.11

aby

1.07

buster

0.93

 thickness

0.93

clock

0.93

paper

0.92

 wall

0.91

tops

0.90

top

0.90

Activations Density 0.023%

words related to walls

references to walls and barriers

No Known Activations