INDEX

Explanations

details or elements from a variety of different topics or sources

oai_token-act-pair · gpt-3.5-turbo

references to notable controversies and plot elements in media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ãĤ®

-0.77

ITNESS

-0.69

)]

-0.66

entin

-0.65

Percent

-0.58

after

-0.57

ificant

-0.57

ctuary

-0.56

ãĥĻ

-0.56

ãĤ±

-0.56

POSITIVE LOGITS

 seamlessly

1.01

 nicely

0.96

 sensibilities

0.86

 effortlessly

0.84

 tropes

0.83

 beautifully

0.82

 pioneered

0.79

 themes

0.77

into

0.75

 eleg

0.75

Activations Density 0.674%

details or elements from a variety of different topics or sources

references to notable controversies and plot elements in media

No Comments

No Known Activations