INDEX

Explanations

sequences starting with specific details or actions followed by a subsequent event or action

oai_token-act-pair · gpt-3.5-turbo

instances of sequential actions or events

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

aez

-0.67

orum

-0.67

scription

-0.65

holder

-0.65

cap

-0.62

sth

-0.62

venture

-0.62

md

-0.61

Bie

-0.60

chio

-0.60

POSITIVE LOGITS

 proceeded

0.95

 proceed

0.78

 succumb

0.73

Ļ½

0.72

srf

0.71

ŃĶ

0.71

 vanish

0.70

EStream

0.70

 reload

0.68

 disappear

0.68

Activations Density 0.053%

sequences starting with specific details or actions followed by a subsequent event or action

instances of sequential actions or events

No Comments

No Known Activations