INDEX

Explanations

mentions of values and principles

oai_token-act-pair · gpt-3.5-turbo

arguments related to morality and ethical considerations in societal frameworks

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

lbs

-0.72

heast

-0.65

Pwr

-0.65

NES

-0.63

UFC

-0.61

 Sprint

-0.60

tips

-0.59

VIP

-0.59

laun

-0.59

 Emergency

-0.59

POSITIVE LOGITS

 epist

1.15

 philosophers

0.97

 presupp

0.96

 insofar

0.95

 empirical

0.92

 normative

0.91

 implicitly

0.89

 subjective

0.86

 intrinsically

0.86

 empir

0.86

Activations Density 2.124%

mentions of values and principles

arguments related to morality and ethical considerations in societal frameworks

No Comments

No Known Activations