INDEX

Explanations

phrases related to providing or receiving help or assistance

oai_token-act-pair · gpt-3.5-turbo

contexts involving assistance and support

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

cars

-0.67

mb

-0.64

nen

-0.63

iannopoulos

-0.63

bang

-0.63

ults

-0.63

ther

-0.62

fare

-0.60

ndra

-0.60

place

-0.60

POSITIVE LOGITS

 with

0.68

 financially

0.68

 tremendously

0.67

ive

0.66

icho

0.66

hooting

0.65

 Desk

0.65

 guiIcon

0.61

 assisting

0.60

 compat

0.60

Activations Density 0.061%

phrases related to providing or receiving help or assistance

contexts involving assistance and support

No Comments

No Known Activations