INDEX

Explanations

phrases related to real-world scenarios or experiences

oai_token-act-pair · gpt-3.5-turbo

references to real-world context and experiences

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

ressed

-0.75

ressing

-0.71

ategories

-0.68

orate

-0.67

rons

-0.66

Bone

-0.66

RAG

-0.64

eded

-0.63

adding

-0.63

alos

-0.62

POSITIVE LOGITS

 scenarios

0.87

 situations

0.78

 counterpart

0.78

 scenario

0.75

 Adventures

0.74

naissance

0.74

 embodiment

0.72

 counterparts

0.72

 physics

0.72

 applications

0.70

Activations Density 0.038%

phrases related to real-world scenarios or experiences

references to real-world context and experiences

No Comments

No Known Activations