INDEX

Explanations

words related to sudden increase or rise in something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "spike" and its variations, indicating a focus on significant increases or changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

İ

-0.79

sburg

-0.68

bis

-0.67

 Incarnation

-0.67

phis

-0.65

mate

-0.65

voc

-0.64

vironments

-0.64

isans

-0.63

ographies

-0.63

POSITIVE LOGITS

olicy

0.78

 spike

0.76

 spikes

0.74

balls

0.71

rites

0.67

lar

0.66

HAEL

0.65

ãĥ©ãĥ³

0.64

isson

0.64

 sidx

0.63

Activations Density 0.017%

words related to sudden increase or rise in something

occurrences of the word "spike" and its variations, indicating a focus on significant increases or changes

No Comments

No Known Activations