INDEX

Explanations

words related to positivity or benefit

oai_token-act-pair · gpt-3.5-turbo

terms related to positive outcomes or advantages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Wolves

-0.71

Hun

-0.68

Rush

-0.68

buck

-0.67

pper

-0.66

Bur

-0.65

á

-0.65

 Fever

-0.64

 Barcl

-0.63

hani

-0.63

POSITIVE LOGITS

 beneficial

0.90

icial

0.88

iciary

0.85

rative

0.78

 destro

0.78

 synerg

0.75

 agre

0.74

tarian

0.74

chwitz

0.73

ritional

0.72

Activations Density 0.010%

words related to positivity or benefit

terms related to positive outcomes or advantages

No Comments

No Known Activations