INDEX

Explanations

phrases related to decision-making

oai_token-act-pair · gpt-3.5-turbo

instances of the word "decide" and its variations, indicating decisions or choices being made

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

oil

-0.73

isha

-0.73

conn

-0.73

VIDEO

-0.71

atha

-0.68

href

-0.68

aired

-0.66

iere

-0.66

athi

-0.66

 tremend

-0.65

POSITIVE LOGITS

 whether

0.85

 decide

0.77

 calculus

0.76

 decides

0.73

 Garc

0.71

lass

0.70

ters

0.69

 deciding

0.68

 ACTIONS

0.66

 decisions

0.64

Activations Density 0.031%

phrases related to decision-making

instances of the word "decide" and its variations, indicating decisions or choices being made

No Comments

No Known Activations