INDEX

Explanations

words related to interception or intercepting

oai_token-act-pair · gpt-3.5-turbo

terms related to interception in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Graph

-0.69

pet

-0.68

Stone

-0.67

Sort

-0.67

adders

-0.66

Myth

-0.66

thumbnails

-0.64

Aid

-0.63

ternity

-0.63

Benz

-0.62

POSITIVE LOGITS

 intercept

1.23

 intercepted

1.01

rons

0.96

ors

0.91

ãĥ¼ãĥĨãĤ£

0.85

ibles

0.81

uality

0.81

ially

0.81

abad

0.79

inel

0.77

Activations Density 0.008%

words related to interception or intercepting

terms related to interception in various contexts

No Comments

No Known Activations