INDEX

Explanations

phrases related to making judgments or assessments of situations or individuals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "judge" and its variants 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

adra

-0.86

ulic

-0.80

lund

-0.79

ols

-0.73

jc

-0.71

heny

-0.71

hall

-0.70

jet

-0.70

uctions

-0.70

Bio

-0.69

POSITIVE LOGITS

 harshly

1.00

 judging

0.90

 whether

0.86

 judgement

0.85

 fairness

0.83

worthiness

0.82

 judgment

0.81

 objectively

0.78

 qualifications

0.73

 criteria

0.72

Activations Density 0.045%

phrases related to making judgments or assessments of situations or individuals

instances of the word "judge" and its variants in various contexts

No Comments

No Known Activations