INDEX

Explanations

terms related to decision-making

oai_token-act-pair · gpt-3.5-turbo

references to decisions and judgment-making processes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uum

-0.73

agogue

-0.67

hibit

-0.66

itute

-0.64

strip

-0.64

esc

-0.63

ew

-0.62

porter

-0.61

chant

-0.60

uu

-0.60

POSITIVE LOGITS

 decisions

3.67

 decision

2.31

 choices

2.26

 judgments

2.10

 rulings

1.85

 Decision

1.74

 conclusions

1.61

 mistakes

1.58

 actions

1.49

 opinions

1.48

Activations Density 0.016%

terms related to decision-making

references to decisions and judgment-making processes

No Comments

No Known Activations