INDEX

Explanations

words related to something long-lasting or enduring

oai_token-act-pair · gpt-3.5-turbo

references to enduring or long-lasting effects and impacts

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

ramid

-1.04

alon

-1.01

 Cosponsors

-0.95

aucus

-0.86

ologies

-0.82

ioch

-0.78

ses

-0.78

alion

-0.77

umbn

-0.77

riad

-0.75

POSITIVE LOGITS

 lasting

1.09

 adolesc

0.89

lasting

0.82

Effects

0.81

 consequences

0.80

 isot

0.79

 memories

0.77

 effects

0.77

åĬ

0.77

 gratification

0.73

Activations Density 0.018%

words related to something long-lasting or enduring

references to enduring or long-lasting effects and impacts

No Comments

No Known Activations