INDEX

Explanations

words related to relationships or associations between different entities

oai_token-act-pair · gpt-3.5-turbo

references to connections or relationships 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 @ 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

Ħ¢

-0.90

inse

-0.68

avis

-0.67

VS

-0.66

vae

-0.65

reat

-0.63

oeuv

-0.62

 jaws

-0.62

prus

-0.61

geries

-0.61

POSITIVE LOGITS

 connection

1.20

connection

1.02

 connections

0.97

connected

0.97

connect

0.92

ioned

0.90

 connected

0.90

 connect

0.89

ability

0.87

 reconnect

0.85

Activations Density 0.014%

words related to relationships or associations between different entities

references to connections or relationships in various contexts

No Comments

No Known Activations