INDEX

Explanations

terms related to products or concepts that are described as "free" in some context

oai_token-act-pair · gpt-3.5-turbo

instances of the word "free" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

aft

-0.74

 precinct

-0.67

 exempl

-0.64

 deputies

-0.64

 divers

-0.62

 helicopters

-0.62

 Pradesh

-0.62

 veins

-0.61

bow

-0.61

 props

-0.60

POSITIVE LOGITS

free

4.11

Free

2.82

FREE

2.38

 free

2.11

 Free

1.97

 FREE

1.83

freedom

1.54

lessly

1.38

fre

1.34

less

1.33

Activations Density 0.017%

terms related to products or concepts that are described as "free" in some context

instances of the word "free" in various contexts

No Comments

No Known Activations