INDEX

Explanations

correlations between different variables or factors

oai_token-act-pair · gpt-3.5-turbo

references to correlation in research or data analysis contexts

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

anas

-0.81

 Citiz

-0.76

arde

-0.76

bern

-0.74

Sov

-0.73

hoff

-0.73

bold

-0.72

fare

-0.72

oeuv

-0.71

thur

-0.71

POSITIVE LOGITS

 coefficient

1.38

 coefficients

1.21

 correlate

1.01

 correlation

0.99

relation

0.90

 correlations

0.84

SHIP

0.79

 correlates

0.78

 linking

0.77

ability

0.74

Activations Density 0.015%

correlations between different variables or factors

references to correlation in research or data analysis contexts

No Comments

No Known Activations