INDEX

Explanations

words related to a specific type of pepper - cayenne pepper

oai_token-act-pair · gpt-3.5-turbo

mentions of cayenne pepper

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

rush

-0.74

reads

-0.74

annis

-0.73

 Seym

-0.70

avorite

-0.69

alien

-0.69

room

-0.68

upon

-0.65

DPR

-0.65

 mathemat

-0.65

POSITIVE LOGITS

clave

0.96

enne

0.94

sie

0.91

cil

0.86

ned

0.84

hoe

0.81

eteen

0.81

fer

0.80

wald

0.79

lde

0.78

Activations Density 0.011%

words related to a specific type of pepper - cayenne pepper

mentions of cayenne pepper

No Comments

No Known Activations