INDEX

Explanations

terms related to measurement, assessment, and quantification

oai_token-act-pair · gpt-3.5-turbo

terms related to scales or indices used for measurement or assessment

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

atre

-0.74

Tai

-0.70

IDA

-0.69

din

-0.69

hai

-0.68

Sov

-0.67

BuyableInstoreAndOnline

-0.67

DVD

-0.67

Anth

-0.66

scrib

-0.66

POSITIVE LOGITS

 determining

1.02

 variables

0.95

 Predict

0.94

 predicting

0.92

 quant

0.92

 predictive

0.91

 predictor

0.90

 determines

0.89

 assessing

0.87

ministic

0.87

Activations Density 0.408%

terms related to measurement, assessment, and quantification

terms related to scales or indices used for measurement or assessment

No Comments

No Known Activations