INDEX

Explanations

terms related to mythology

oai_token-act-pair · gpt-3.5-turbo

terms related to mythology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 warr

-0.66

IPM

-0.62

 Jessie

-0.62

 licences

-0.61

Policy

-0.60

 Policy

-0.60

 Stra

-0.59

 horizont

-0.58

 leases

-0.57

 licenses

-0.57

POSITIVE LOGITS

ril

1.28

icist

1.25

ological

1.18

ologies

1.14

busters

1.12

olog

1.09

ic

0.99

arily

0.97

emonic

0.96

buster

0.94

Activations Density 0.071%

terms related to mythology

terms related to mythology

No Comments

No Known Activations