INDEX

Explanations

expressions related to mathematical operations and numbers

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "number" and its variations, along with their respective values

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

rador

-0.92

INTON

-0.81

hire

-0.78

illes

-0.77

rend

-0.77

Sov

-0.77

ovie

-0.73

riot

-0.72

 Shroud

-0.71

axter

-0.71

POSITIVE LOGITS

pad

0.87

plates

0.85

enance

0.78

esses

0.76

mable

0.75

 crunch

0.75

metry

0.74

 digits

0.74

 milliseconds

0.73

 comput

0.72

Activations Density 0.063%

expressions related to mathematical operations and numbers

occurrences of the word "number" and its variations, along with their respective values

No Comments

No Known Activations