INDEX

Explanations

instances of the keyword "Ke" followed by a number, which seems to be a specific category or identifier in the text

oai_token-act-pair · gpt-3.5-turbo

references to the name "Ke" across various contexts

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

etheless

-0.70

syn

-0.66

 Gateway

-0.66

 controllers

-0.62

sburgh

-0.62

 Kinnikuman

-0.61

 Blumenthal

-0.61

 specializing

-0.59

Ort

-0.59

 IMAGES

-0.58

POSITIVE LOGITS

aton

1.18

hma

1.11

eling

1.09

ppel

1.08

jriwal

1.07

SPA

1.07

efe

1.05

ptic

1.04

iji

1.02

pler

1.02

Activations Density 0.019%

instances of the keyword "Ke" followed by a number, which seems to be a specific category or identifier in the text

references to the name "Ke" across various contexts

No Comments

No Known Activations