INDEX

Explanations

strong correlations between different elements or factors mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

discussions or references to correlations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.84

hoff

-0.80

thur

-0.78

ahime

-0.76

bern

-0.73

arde

-0.72

udeb

-0.72

sw

-0.71

 Citiz

-0.69

apo

-0.69

POSITIVE LOGITS

 coefficient

1.25

 coefficients

1.09

 correlate

0.85

nces

0.79

relation

0.78

 correlation

0.75

ifer

0.75

 correlates

0.71

SHIP

0.70

inated

0.69

Activations Density 0.039%

strong correlations between different elements or factors mentioned in the text

discussions or references to correlations

No Comments

No Known Activations