INDEX

Explanations

patterns related to numerical comparisons

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "and" in various 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

monitor

-0.58

apult

-0.58

etitive

-0.57

tul

-0.56

 Focus

-0.56

 Citiz

-0.56

Dul

-0.55

Redd

-0.55

Tracker

-0.54

Aid

-0.53

POSITIVE LOGITS

imore

0.85

PsyNetMessage

0.73

 intersections

0.69

enegger

0.68

ottest

0.66

udeau

0.65

 olds

0.65

renheit

0.63

urses

0.63

 sidx

0.62

Activations Density 0.293%

patterns related to numerical comparisons

occurrences of the word "and" in various contexts

No Comments

No Known Activations