INDEX

Explanations

mentioned words related to messaging or communication platforms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "messaging."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

arte

-0.77

engeance

-0.73

\/\/

-0.71

eln

-0.70

bor

-0.69

biased

-0.69

arson

-0.68

vol

-0.66

================================================================

-0.65

ft

-0.64

POSITIVE LOGITS

 messaging

1.28

 messages

0.97

 Messages

0.88

 goodbye

0.84

 message

0.82

Message

0.78

tons

0.78

 inbox

0.75

 advis

0.74

 calculator

0.73

Activations Density 0.011%

mentioned words related to messaging or communication platforms

occurrences of the word "messaging."

No Comments

No Known Activations