INDEX

Explanations

The neuron is looking for words related to facts or issues

oai_token-act-pair · gpt-3.5-turbo

words related to functionality and practicality 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ãģ¯

-0.73

CHAT

-0.69

Veter

-0.68

Sav

-0.68

âĸĪâĸĪâĸĪâĸĪ

-0.68

Frameworks

-0.67

ARDS

-0.66

ðĿ

-0.66

================

-0.66

YouTube

-0.65

POSITIVE LOGITS

ional

1.40

acia

0.91

ially

0.89

terness

0.85

ities

0.83

 brill

0.82

ised

0.82

ism

0.81

 sized

0.80

 glances

0.79

Activations Density 0.010%

The neuron is looking for words related to facts or issues

words related to functionality and practicality in various contexts

No Comments

No Known Activations