INDEX

Explanations

words related to experiencing or repeating events or memories

oai_token-act-pair · gpt-3.5-turbo

suffixes related to actions or states of being

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

 Slate

-0.91

 Butterfly

-0.80

ãģ®éŃĶ

-0.71

 Dahl

-0.70

 Mehran

-0.70

 Unloaded

-0.69

teenth

-0.68

 Lowell

-0.68

 Benson

-0.67

 Hazard

-0.65

POSITIVE LOGITS

ativity

0.95

MpServer

0.84

ciating

0.80

warm

0.80

ndum

0.78

ulous

0.76

owship

0.76

ency

0.75

ENCY

0.74

iety

0.73

Activations Density 0.031%

words related to experiencing or repeating events or memories

suffixes related to actions or states of being

No Comments

No Known Activations