INDEX

Explanations

mentions of specific names, likely related to a particular person or topic

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

istically

-0.92

istic

-0.71

ually

-0.67

ities

-0.65

 Reconstruction

-0.65

icals

-0.64

ãĥĩ

-0.63

senal

-0.63

occ

-0.61

istical

-0.60

POSITIVE LOGITS

orthy

1.10

riter

1.04

olf

0.99

atcher

0.95

inders

0.95

ritten

0.95

erd

0.94

atson

0.94

orld

0.92

ey

0.90

Activations Density 0.076%

mentions of specific names, likely related to a particular person or topic

proper nouns, particularly names and places

No Comments

No Known Activations