INDEX

Explanations

phrases related to decision-making processes

oai_token-act-pair · gpt-3.5-turbo

terms related to decision-making processes and individuals involved in such processes

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

ritch

-0.75

illin

-0.70

ilers

-0.69

sels

-0.69

aint

-0.67

achus

-0.67

 Smile

-0.63

ngth

-0.63

dig

-0.63

ierre

-0.63

POSITIVE LOGITS

 decisions

0.86

 decision

0.82

 exped

0.78

 unanimously

0.77

 deciding

0.75

 reinvest

0.74

 judgement

0.74

 overr

0.74

 ACTIONS

0.74

 direction

0.73

Activations Density 0.295%

phrases related to decision-making processes

terms related to decision-making processes and individuals involved in such processes

No Comments

No Known Activations