INDEX

Explanations

references to quantities of two or three items

oai_token-act-pair · gpt-3.5-turbo

references to quantities and numerical values in relation to groups or entities

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

matter

-0.90

 Akin

-0.69

kell

-0.67

Gene

-0.64

ovie

-0.64

leigh

-0.61

both

-0.60

zee

-0.60

form

-0.59

Typ

-0.58

POSITIVE LOGITS

 dozen

0.70

 hundred

0.65

 quir

0.64

pires

0.62

 favorites

0.62

ected

0.61

 factors

0.61

IFIC

0.60

 hemisphere

0.60

onnaissance

0.60

Activations Density 0.085%

references to quantities of two or three items

references to quantities and numerical values in relation to groups or entities

No Comments

No Known Activations