INDEX

Explanations

terms related to decision-making

oai_token-act-pair · gpt-3.5-turbo

references to important decisions or choices made in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

english

-0.81

vae

-0.77

eco

-0.69

ubric

-0.67

ingers

-0.66

amen

-0.63

sung

-0.63

izont

-0.63

ewitness

-0.62

atomic

-0.62

POSITIVE LOGITS

 makers

0.97

 decision

0.86

 maker

0.84

 decisions

0.83

 ACTIONS

0.83

 stance

0.74

maker

0.72

ters

0.69

 chose

0.69

jar

0.69

Activations Density 0.033%

terms related to decision-making

references to important decisions or choices made in various contexts

No Comments

No Known Activations