INDEX

Explanations

decisions or mentions of decision-making

oai_token-act-pair · gpt-3.5-turbo

instances of the word "decision" 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ilus

-0.71

aunder

-0.70

ols

-0.68

atures

-0.66

esters

-0.65

ets

-0.63

Sources

-0.63

hin

-0.62

hidden

-0.62

onge

-0.62

POSITIVE LOGITS

 decision

3.50

 decisions

2.64

 Decision

2.44

 judgement

1.82

 determination

1.76

 choice

1.72

 judgment

1.66

 deciding

1.62

 ruling

1.48

 choices

1.43

Activations Density 0.019%

decisions or mentions of decision-making

instances of the word "decision" in various contexts

No Comments

No Known Activations