INDEX

Explanations

statements summarizing or analyzing arguments

oai_token-act-pair · gpt-3.5-turbo

phrases and concepts that relate to arguments and their structure

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

-0.67

roy

-0.66

Temperature

-0.61

hello

-0.61

dies

-0.60

 Roses

-0.59

Crew

-0.59

 Kobe

-0.58

LOS

-0.58

ggies

-0.57

POSITIVE LOGITS

 methodological

0.89

 empir

0.84

 empirical

0.82

 scholarly

0.80

 descriptive

0.79

 informative

0.78

 factual

0.77

 quotations

0.77

 promulg

0.77

 persuasive

0.77

Activations Density 2.116%

statements summarizing or analyzing arguments

phrases and concepts that relate to arguments and their structure

No Comments

No Known Activations