INDEX

Explanations

proper nouns or specific terms related to technology and products

oai_token-act-pair · gpt-3.5-turbo

references to specific media, brands, or notable events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Joined

-0.71

 annexed

-0.67

 CLSID

-0.64

usalem

-0.61

hiba

-0.59

inki

-0.59

oso

-0.59

Downloadha

-0.58

itton

-0.57

 vacated

-0.57

POSITIVE LOGITS

 varies

0.85

 depends

0.75

viz

0.72

 differs

0.71

 methodology

0.67

 outweigh

0.65

 nutshell

0.65

yssey

0.65

 revolves

0.64

mma

0.64

Activations Density 0.458%

proper nouns or specific terms related to technology and products

references to specific media, brands, or notable events

No Comments

No Known Activations