INDEX

Explanations

references to a specific word "Twe" in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific brand or product related to technology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥĩ

-0.77

inated

-0.73

inating

-0.70

senal

-0.70

ozo

-0.67

iott

-0.66

inates

-0.64

ONT

-0.64

 predatory

-0.63

UAL

-0.63

POSITIVE LOGITS

eden

1.14

Twe

0.99

ety

0.92

akens

0.88

edy

0.88

ollen

0.87

Twe

0.87

riter

0.85

ritten

0.85

ets

0.85

Activations Density 0.019%

references to a specific word "Twe" in the text

mentions of a specific brand or product related to technology

No Comments

No Known Activations