INDEX

Explanations

words related to progress or change

oai_token-act-pair · gpt-3.5-turbo

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

 thirds

-0.63

 respectively

-0.61

QC

-0.59

 ______

-0.58

 Fiji

-0.57

 cholesterol

-0.54

+.

-0.54

Float

-0.52

DERR

-0.52

POSITIVE LOGITS

 stemmed

1.24

 stems

1.17

 coincided

1.12

 extends

1.10

 intensified

1.09

 culminated

1.05

 began

1.05

 persists

1.04

 prompted

1.03

 arose

1.02

Activations Density 0.291%

words related to progress or change

No Comments

No Known Activations