INDEX

Explanations

phrases indicating a current situation or time period

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the current or present 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

ashtra

-0.79

boa

-0.73

sym

-0.73

aughed

-0.71

 Berm

-0.68

adr

-0.66

asus

-0.66

rals

-0.65

onel

-0.64

ammy

-0.63

POSITIVE LOGITS

adays

1.02

èª

0.85

here

0.82

å¸

0.76

 reversible

0.75

rox

0.71

 scen

0.70

 slated

0.69

 defunct

0.69

comings

0.64

Activations Density 0.033%

phrases indicating a current situation or time period

phrases emphasizing the current or present time

No Comments

No Known Activations