INDEX

Explanations

mentions of a specific entity or topic within a longer discussion context

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

itiz

-0.77

ional

-0.72

irds

-0.68

abe

-0.64

Topics

-0.62

pointers

-0.62

 owes

-0.62

#$

-0.62

 malf

-0.61

uty

-0.61

POSITIVE LOGITS

 meantime

1.66

 midst

1.37

 aftermath

1.26

 absence

1.23

 context

1.07

 simplest

1.05

 guise

1.04

 ensuing

1.01

 wake

1.00

 meanwhile

0.98

Activations Density 0.167%

mentions of a specific entity or topic within a longer discussion context

instances of the word "the"

No Comments

No Known Activations