INDEX

Explanations

phrases related to sudden actions or appearances

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "pop" and its variations, often related to sudden appearances or actions

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

Negative Logits

 assisting

-0.60

 preventing

-0.59

 restoring

-0.59

journal

-0.58

how

-0.57

 Children

-0.56

 Failure

-0.56

 Generation

-0.55

 juveniles

-0.55

 succession

-0.55

POSITIVE LOGITS

ãĥ³ãĤ¸

0.81

kered

0.79

 onto

0.71

 into

0.70

 toes

0.70

CHAT

0.70

toe

0.70

 belly

0.69

 awake

0.67

rets

0.67

Activations Density 0.354%

phrases related to sudden actions or appearances

occurrences of the word "pop" and its variations, often related to sudden appearances or actions

No Known Activations