INDEX

Explanations

objects or entities that are of interest or relevance in a given context

oai_token-act-pair · gpt-3.5-turbo

nouns related to animals and objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Beer

-0.80

 Dhabi

-0.75

 Beer

-0.71

iband

-0.70

 "$:/

-0.70

-0.67

Music

-0.64

pmwiki

-0.64

 Comics

-0.62

 Music

-0.62

POSITIVE LOGITS

 contained

0.75

fighter

0.73

 survived

0.71

 belonged

0.70

 transported

0.68

 weighed

0.67

 exhibited

0.65

 pictured

0.64

fighters

0.64

 discharged

0.64

Activations Density 0.481%

objects or entities that are of interest or relevance in a given context

nouns related to animals and objects

No Comments

No Known Activations