INDEX

Explanations

words related to mystery

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of mystery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ript

-0.78

ippy

-0.78

obe

-0.77

umbnail

-0.77

zar

-0.76

ensible

-0.76

orses

-0.75

apsed

-0.74

sen

-0.73

arf

-0.73

POSITIVE LOGITS

 mystery

1.00

 mysteries

0.99

 Mystery

0.98

 Mysteries

0.86

 solved

0.81

stery

0.77

 unsolved

0.77

 myster

0.76

 abound

0.75

 trail

0.75

Activations Density 0.016%

words related to mystery

terms related to the concept of mystery

No Comments

No Known Activations