INDEX

Explanations

mentions of residents in various contexts or situations

oai_token-act-pair · gpt-3.5-turbo

mentions of "residents."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

anche

-0.81

icer

-0.76

ategory

-0.71

usha

-0.70

Exec

-0.67

nir

-0.66

Session

-0.65

ripp

-0.64

catentry

-0.63

olicy

-0.63

POSITIVE LOGITS

hips

1.19

folk

1.13

hip

1.10

 living

0.90

 Residents

0.89

 residents

0.85

Residents

0.83

who

0.81

ites

0.79

 resident

0.79

Activations Density 0.044%

mentions of residents in various contexts or situations

mentions of "residents."

No Comments

No Known Activations