INDEX

Explanations

phrases related to decision-making and choices

oai_token-act-pair · gpt-3.5-turbo

questions or uncertainties related to decision-making and influence

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 WATCHED

-0.70

then

-0.57

Fla

-0.55

 Ortiz

-0.54

 THEN

-0.52

TOM

-0.51

 Princ

-0.51

'/

-0.51

Hut

-0.50

POSITIVE LOGITS

 altogether

1.09

 outright

0.96

 simply

0.91

depending

0.81

 merely

0.81

 unlucky

0.79

abouts

0.78

 downright

0.77

 alternatively

0.72

 Marketable

0.71

Activations Density 0.372%

phrases related to decision-making and choices

questions or uncertainties related to decision-making and influence

No Comments

No Known Activations