INDEX

Explanations

references to current events or actions happening now

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "now."

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

obos

-0.66

monds

-0.65

lua

-0.63

EVA

-0.62

 Died

-0.60

ogi

-0.60

Must

-0.60

 Hind

-0.60

 Dynamo

-0.59

 Conc

-0.59

POSITIVE LOGITS

adays

1.25

here

1.05

 underway

0.96

 defunct

0.95

 extinct

0.87

 officially

0.86

 slated

0.83

 obsolete

0.80

osponsors

0.80

aukee

0.80

Activations Density 0.057%

references to current events or actions happening now

occurrences of the word "now."

No Comments

No Known Activations