INDEX

Explanations

features or characteristics mentioned in a technical context

oai_token-act-pair · gpt-3.5-turbo

instances of the word "feature" and its variations related to technological attributes or functionalities

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

sis

-0.77

oner

-0.77

abama

-0.70

cffffcc

-0.70

alg

-0.66

agher

-0.66

aline

-0.65

kos

-0.65

externalActionCode

-0.65

eneg

-0.65

POSITIVE LOGITS

Feature

0.87

ivity

0.86

iveness

0.81

 features

0.80

 Features

0.80

hered

0.80

Features

0.79

ttes

0.78

feature

0.75

enment

0.74

Activations Density 0.041%

features or characteristics mentioned in a technical context

instances of the word "feature" and its variations related to technological attributes or functionalities

No Comments

No Known Activations