INDEX

Explanations

references to television and TV-related terms

oai_token-act-pair · gpt-3.5-turbo

references to television

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xual

-0.90

ussen

-0.89

cies

-0.79

forth

-0.78

iveness

-0.77

staking

-0.73

ctuary

-0.72

quez

-0.71

cific

-0.69

POSITIVE LOGITS

trop

0.99

 Trop

0.96

 Shows

0.90

ILLE

0.86

 Everywhere

0.80

TVs

0.80

Guide

0.79

 presenter

0.79

plays

0.77

IE

0.77

Activations Density 0.022%

references to television and TV-related terms

references to television

No Comments

No Known Activations