INDEX

Explanations

phrases related to specific technical terms, possibly from a technical manual or dataset

oai_token-act-pair · gpt-3.5-turbo

prominent references to unique products or items

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

Ó

-0.95

Players

-0.93

Ãĥ

-0.92

Ì¶

-0.88

Job

-0.87

Package

-0.87

Justice

-0.84

Act

-0.84

Intel

-0.83

API

-0.83

POSITIVE LOGITS

 flats

0.96

 hover

0.95

wed

0.95

 grid

0.94

 shin

0.92

 rainbow

0.92

 bunk

0.90

 quake

0.89

 shar

0.88

tee

0.88

Activations Density 1.112%

phrases related to specific technical terms, possibly from a technical manual or dataset

prominent references to unique products or items

No Comments

No Known Activations