INDEX

Explanations

words related to causality and actions in past scenarios

oai_token-act-pair · gpt-3.5-turbo

references to the pronoun "it" and quantifiers in a variety of contexts

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

 Making

-0.63

tern

-0.62

 Hick

-0.60

 Pants

-0.59

lash

-0.59

 Comfort

-0.58

bell

-0.57

 Invisible

-0.57

 Marion

-0.57

Ark

-0.56

POSITIVE LOGITS

 evidenced

0.90

 actionGroup

0.89

 Âł Âł Âł Âł

0.79

[|

0.78

 wont

0.78

 Âł Âł Âł Âł Âł Âł Âł Âł

0.75

 previously

0.71

çĶ°

0.70

 attest

0.67

 ());

0.66

Activations Density 0.186%

words related to causality and actions in past scenarios

references to the pronoun "it" and quantifiers in a variety of contexts

No Comments

No Known Activations