INDEX

Explanations

keywords related to data processing instructions and input information

oai_token-act-pair · gpt-3.5-turbo

instances of the term "input" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Seraph

-0.72

astern

-0.65

neys

-0.65

itect

-0.62

adder

-0.61

llan

-0.61

esa

-0.60

ETA

-0.60

ISS

-0.59

 Apart

-0.58

POSITIVE LOGITS

ted

1.06

enza

0.93

 inputs

0.92

 input

0.89

ting

0.87

ters

0.85

 "$:/

0.76

ierrez

0.76

input

0.75

 guiName

0.74

Activations Density 0.010%

keywords related to data processing instructions and input information

instances of the term "input" in various contexts

No Comments

No Known Activations