INDEX

Explanations

phrases related to actions or processes accomplished or achieved by means of something or someone

oai_token-act-pair · gpt-3.5-turbo

instances of the word "through."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

etus

-0.81

ãĤ·

-0.69

CTV

-0.68

ern

-0.66

qua

-0.66

Ont

-0.66

ãĥī

-0.66

wu

-0.65

atron

-0.65

hene

-0.64

POSITIVE LOGITS

 sheer

1.20

 inaction

1.08

 intermedi

1.08

 attrition

1.07

 repetition

0.91

 obscurity

0.89

 proxies

0.87

gone

0.87

 partnerships

0.87

 experimentation

0.86

Activations Density 0.061%

phrases related to actions or processes accomplished or achieved by means of something or someone

instances of the word "through."

No Comments

No Known Activations