INDEX

Explanations

phrases indicating clarification or explanation

oai_token-act-pair · gpt-3.5-turbo

conditional statements and qualifications in the text

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

 awoken

-0.76

anded

-0.72

accompan

-0.65

handled

-0.62

fed

-0.61

footed

-0.61

figured

-0.59

oru

-0.57

 voic

-0.57

ļéĨĴ

-0.57

POSITIVE LOGITS

 necessarily

0.88

 exaggeration

0.86

 anymore

0.81

 exagger

0.76

 lightly

0.71

 dissu

0.71

imilar

0.71

azes

0.69

 discouraged

0.69

 anything

0.68

Activations Density 0.414%

phrases indicating clarification or explanation

conditional statements and qualifications in the text

No Comments

No Known Activations