INDEX

Explanations

phrases related to rules and adherence to them

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or risk

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

eur

-0.61

grow

-0.61

wx

-0.61

growth

-0.61

 Liter

-0.59

help

-0.57

 yours

-0.56

 tips

-0.56

anooga

-0.55

foundation

-0.55

POSITIVE LOGITS

 unilaterally

0.82

 incorrectly

0.82

 inexpl

0.79

 inconsist

0.78

 excessively

0.78

 disproportionately

0.78

 concurrently

0.76

 consecut

0.76

 unexpectedly

0.75

 excluded

0.75

Activations Density 1.052%

phrases related to rules and adherence to them

phrases indicating uncertainty or risk

No Comments

No Known Activations