INDEX

Explanations

adjectives and phrases related to rankings, positions, and comparisons

oai_token-act-pair · gpt-3.5-turbo

financial references involving numbers and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

\\\\\\\\

-0.66

>>>>>>>>

-0.62

 citiz

-0.58

 volunte

-0.57

 friends

-0.57

untled

-0.57

Anonymous

-0.56

 Rena

-0.55

Friends

-0.55

 Pets

-0.54

POSITIVE LOGITS

omial

0.75

 chords

0.74

 theorem

0.73

rhy

0.73

 decimal

0.72

 arithmetic

0.72

 integers

0.70

 coefficients

0.70

 syll

0.69

 ratio

0.68

Activations Density 1.103%

adjectives and phrases related to rankings, positions, and comparisons

financial references involving numbers and measurements

No Comments

No Known Activations