INDEX

Explanations

phrases related to cause and effect, specifically focusing on actions leading to a particular outcome

oai_token-act-pair · gpt-3.5-turbo

the word "the" and related phrases indicating significance or attention to specific subjects

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

>:

-0.92

leeve

-0.78

ttp

-0.77

-0.76

ossal

-0.76

Supported

-0.74

ãĤ´ãĥ³

-0.74

-->

-0.74

vised

-0.73

perse

-0.71

POSITIVE LOGITS

 brakes

1.09

 entire

1.08

lid

1.07

 needle

1.06

 curtain

1.00

 envelope

0.97

 tide

0.97

 spotlight

0.95

 blame

0.93

 burden

0.93

Activations Density 0.241%

phrases related to cause and effect, specifically focusing on actions leading to a particular outcome

the word "the" and related phrases indicating significance or attention to specific subjects

No Comments

No Known Activations