INDEX

Explanations

phrases and sentences that contain the word "based" to make decisions or judgments

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate conditions or criteria for making decisions

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

ertain

-0.77

opsis

-0.70

igmat

-0.69

imilation

-0.64

Reviewer

-0.64

roth

-0.62

jay

-0.62

RAG

-0.61

LCS

-0.61

ggies

-0.61

POSITIVE LOGITS

aneously

0.68

 upstream

0.62

 behalf

0.61

 favour

0.60

xes

0.60

 Omaha

0.59

 weekends

0.58

 intervals

0.58

 Lund

0.57

 spring

0.56

Activations Density 0.746%

phrases and sentences that contain the word "based" to make decisions or judgments

phrases that indicate conditions or criteria for making decisions

No Comments

No Known Activations