INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals and associated identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ModLoader

-0.79

 Appalach

-0.77

itiveness

-0.67

 Appalachian

-0.67

Topics

-0.65

stown

-0.65

PLIED

-0.64

sburgh

-0.63

HMS

-0.62

earchers

-0.62

POSITIVE LOGITS

ende

0.92

enz

0.85

iani

0.84

oso

0.83

etti

0.81

otti

0.81

ache

0.79

zen

0.79

arte

0.79

isi

0.78

Activations Density 0.244%

names of individuals

proper nouns, particularly names of individuals and associated identifiers

No Comments

No Known Activations