INDEX

Explanations

passages related to commentary or critique

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate evidence, assertion, or definitive statements

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

ologue

-0.65

 vanquished

-0.63

 consulted

-0.63

 Britann

-0.63

lov

-0.63

 WRITE

-0.62

 photographed

-0.61

 experimented

-0.61

 photograp

-0.60

 dressed

-0.58

POSITIVE LOGITS

soType

0.75

ADRA

0.71

 deterrence

0.70

 suspicions

0.69

 deterrent

0.69

quickShipAvailable

0.68

emi

0.68

trump

0.68

incent

0.68

IER

0.66

Activations Density 0.932%

passages related to commentary or critique

phrases that indicate evidence, assertion, or definitive statements

No Comments

No Known Activations