INDEX

Explanations

years related to specific events or activities

oai_token-act-pair · gpt-3.5-turbo

years, particularly in a context related to seasons or events

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

imore

-0.79

amber

-0.71

onet

-0.70

anch

-0.69

ess

-0.69

unders

-0.67

prime

-0.67

orney

-0.67

hedral

-0.66

 notor

-0.65

POSITIVE LOGITS

å¹

1.11

 edition

0.76

ãģ®éŃĶ

0.73

 Update

0.70

 STATS

0.68

 Stats

0.67

 Revision

0.67

 Remastered

0.66

 Recap

0.66

 Audi

0.65

Activations Density 0.074%

years related to specific events or activities

years, particularly in a context related to seasons or events

No Comments

No Known Activations