INDEX

Explanations

numerical quantities or counts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "number" followed by numerical values

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

missible

-0.77

sein

-0.74

rador

-0.74

 Despair

-0.73

idden

-0.71

anium

-0.69

rament

-0.66

 separat

-0.66

 Thou

-0.64

agate

-0.64

POSITIVE LOGITS

otom

0.71

plate

0.68

number

0.66

of

0.66

onement

0.66

encies

0.64

othe

0.63

0.62

 thousand

0.62

metry

0.60

Activations Density 0.027%

numerical quantities or counts

occurrences of the word "number" followed by numerical values

No Comments

No Known Activations