INDEX

Explanations

words related to dependence or variability

oai_token-act-pair · gpt-3.5-turbo

phrases indicating dependency or conditionality

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥĪ

-0.69

jer

-0.66

luaj

-0.66

BSD

-0.65

jam

-0.64

adia

-0.64

uck

-0.64

seys

-0.62

????

-0.62

ãĤ´ãĥ³

-0.62

POSITIVE LOGITS

 whether

1.67

how

1.40

whether

1.24

 thickness

1.08

 quantity

1.06

Whether

1.05

 what

1.04

 availability

1.03

 length

1.02

 severity

1.01

Activations Density 0.287%

words related to dependence or variability

phrases indicating dependency or conditionality

No Comments

No Known Activations