INDEX

Explanations

determiners describing specificity and quantity.

oai_token-act-pair · gpt-3.5-turbo

references to well-known individuals 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

ulhu

-0.78

Phi

-0.75

 DRAG

-0.74

Ń·

-0.72

 Noir

-0.72

 Compass

-0.71

 Zombie

-0.68

 Midnight

-0.68

XD

-0.68

 Slide

-0.66

POSITIVE LOGITS

enough

1.19

sized

1.14

connected

1.09

sounding

1.04

equipped

1.03

position

1.03

function

1.02

aligned

1.02

sided

1.01

backed

1.00

Activations Density 0.047%

**determiners describing specificity and quantity.**

references to well-known individuals or entities

No Comments

No Known Activations

determiners describing specificity and quantity.