INDEX

Explanations

occurrences of a specific number

oai_token-act-pair · gpt-3.5-turbo

references to quantity or count

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rador

-0.82

 Piercing

-0.72

adena

-0.65

_-

-0.62

 slump

-0.61

ataka

-0.60

endon

-0.60

 toast

-0.60

 issuer

-0.59

 Enhancement

-0.58

POSITIVE LOGITS

metry

0.88

enance

0.74

(~

0.73

 numbers

0.73

dot

0.71

(>

0.69

number

0.69

of

0.68

0.67

een

0.67

Activations Density 0.035%

occurrences of a specific number

references to quantity or count

No Comments

No Known Activations