INDEX

Explanations

words related to negative or distressing situations and events

oai_token-act-pair · gpt-3.5-turbo

references to negative experiences or conditions, particularly those involving being troubled or affected by past events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

reme

-0.78

ettel

-0.78

raviolet

-0.70

uber

-0.67

iannopoulos

-0.66

utenberg

-0.66

endiary

-0.66

ighters

-0.65

oulos

-0.65

quickShipAvailable

-0.65

POSITIVE LOGITS

 havoc

1.03

 plagued

0.92

 plag

0.88

luster

0.75

ĸļ

0.74

 haunted

0.71

gling

0.70

Sym

0.70

asus

0.69

 headaches

0.67

Activations Density 0.059%

words related to negative or distressing situations and events

references to negative experiences or conditions, particularly those involving being troubled or affected by past events

No Comments

No Known Activations