INDEX

Explanations

phrases related to making judgments

oai_token-act-pair · gpt-3.5-turbo

references to judgment or evaluations of people and actions

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

ohyd

-0.81

iliar

-0.79

uld

-0.79

ospons

-0.77

adra

-0.77

oteric

-0.70

dayName

-0.70

jc

-0.69

jri

-0.69

iere

-0.68

POSITIVE LOGITS

 judging

0.85

jud

0.80

ģĸ

0.77

 Gorsuch

0.74

 judgment

0.73

 judgement

0.72

 Advocate

0.70

 harshly

0.70

 judgments

0.70

lessly

0.70

Activations Density 0.030%

phrases related to making judgments

references to judgment or evaluations of people and actions

No Comments

No Known Activations