INDEX

Explanations

phrases related to significant events or actions

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly semicolons

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

se

-0.73

urg

-0.68

orts

-0.66

ema

-0.65

aved

-0.64

ħĭ

-0.64

ilot

-0.64

inki

-0.64

Accessory

-0.62

ene

-0.62

POSITIVE LOGITS

 moreover

1.24

 furthermore

1.23

 namely

1.16

 hence

1.12

 however

1.09

 consequently

1.08

 alternatively

1.07

 meanwhile

1.05

-)

1.01

 indeed

1.01

Activations Density 0.057%

phrases related to significant events or actions

punctuation marks, particularly semicolons

No Comments

No Known Activations