INDEX

Explanations

references to locations or individuals named "Jude"

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Jude" and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ierre

-0.86

quished

-0.86

aired

-0.81

pmwiki

-0.79

 Dragonbound

-0.79

EDIT

-0.78

NetMessage

-0.74

Marginal

-0.67

ily

-0.67

OWER

-0.67

POSITIVE LOGITS

 Galile

0.86

nton

0.79

ksh

0.78

itaire

0.73

ucl

0.69

ī

0.69

encia

0.68

quo

0.67

nai

0.66

ept

0.66

Activations Density 0.024%

references to locations or individuals named "Jude"

mentions of the term "Jude" and related concepts

No Comments

No Known Activations