INDEX

Explanations

abbreviations or acronyms often involving political entities

oai_token-act-pair · gpt-3.5-turbo

references to legislative bills or proposals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ovich

-0.72

lessly

-0.67

esan

-0.61

 coincide

-0.60

enegger

-0.60

 modem

-0.60

owsky

-0.59

yright

-0.58

 utilitarian

-0.57

 roam

-0.57

POSITIVE LOGITS

Ct

0.84

0.78

outher

0.77

RNA

0.76

0.74

DAY

0.73

0.72

Ws

0.71

Activations Density 0.036%

abbreviations or acronyms often involving political entities

references to legislative bills or proposals

No Comments

No Known Activations