INDEX

Explanations

words related to change or development over time

oai_token-act-pair · gpt-3.5-turbo

terms related to evolution and change over time

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

pled

-0.71

zzi

-0.67

olicited

-0.66

avering

-0.66

ellow

-0.65

Assembly

-0.65

holder

-0.64

sol

-0.64

AMA

-0.63

abel

-0.63

POSITIVE LOGITS

 evolve

0.84

arily

0.81

anwhile

0.80

brates

0.80

etically

0.77

iator

0.76

 extinct

0.70

ives

0.70

brate

0.68

ively

0.68

Activations Density 0.018%

words related to change or development over time

terms related to evolution and change over time

No Comments

No Known Activations