INDEX

Explanations

distinguishing or categorizing information related to multiple instances, locations, or contexts

oai_token-act-pair · gpt-3.5-turbo

concepts related to separation and distinction between entities or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

someone

-0.85

antry

-0.81

urgy

-0.77

Tracker

-0.75

rology

-0.72

uddin

-0.72

cius

-0.71

geist

-0.70

vu

-0.68

pection

-0.68

POSITIVE LOGITS

 paragraphs

1.02

 generations

1.00

 continents

0.96

 factions

0.96

 thirds

0.94

 editions

0.91

 sets

0.89

 successive

0.89

 pairs

0.89

 fronts

0.88

Activations Density 0.120%

distinguishing or categorizing information related to multiple instances, locations, or contexts

concepts related to separation and distinction between entities or categories

No Comments

No Known Activations