INDEX

Explanations

terms related to Bayesian analysis and mathematical probability distributions

oai_token-act-pair · gpt-3.5-turbo

terms related to Bayesian probability and statistical inference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elight

-0.75

Veter

-0.73

 Veteran

-0.68

 truce

-0.67

 Leban

-0.67

AIR

-0.67

 unofficial

-0.66

 refreshing

-0.65

tips

-0.65

 racks

-0.65

POSITIVE LOGITS

 theorem

0.96

 Theory

0.92

icist

0.92

ensional

0.88

omorph

0.87

igmatic

0.87

rational

0.86

ŃĶ

0.85

 hypothesis

0.84

pair

0.84

Activations Density 0.548%

terms related to Bayesian analysis and mathematical probability distributions

terms related to Bayesian probability and statistical inference

No Comments

No Known Activations