INDEX

Explanations

words related to technology and proper nouns such as names and locations

oai_token-act-pair · gpt-3.5-turbo

recurring terms related to narrative elements and actions

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

onic

-0.92

ogun

-0.90

chens

-0.83

astics

-0.80

hran

-0.80

iquid

-0.78

oly

-0.78

olit

-0.78

ormon

-0.77

ikk

-0.76

POSITIVE LOGITS

vier

0.90

 crow

0.82

âĸ¬

0.78

backs

0.76

å°Ĩ

0.74

lance

0.70

dar

0.69

iott

0.68

 Crimson

0.68

 Tide

0.68

Activations Density 0.022%

words related to technology and proper nouns such as names and locations

recurring terms related to narrative elements and actions

No Comments

No Known Activations