INDEX

Explanations

phrases related to making judgments

oai_token-act-pair · gpt-3.5-turbo

phrases related to judgment and assessment of behavior or actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

iliar

-0.84

adra

-0.78

ospons

-0.77

uld

-0.75

ohyd

-0.73

lished

-0.71

lund

-0.71

iere

-0.70

oteric

-0.69

jc

-0.69

POSITIVE LOGITS

 judging

0.86

jud

0.80

 harshly

0.76

 Gorsuch

0.76

 judgment

0.74

 judgement

0.72

ģĸ

0.69

 unfocusedRange

0.68

phas

0.67

lessly

0.66

Activations Density 0.029%

phrases related to making judgments

phrases related to judgment and assessment of behavior or actions

No Comments

No Known Activations