INDEX

Explanations

phrases expressing challenges, debates, and decisive situations

oai_token-act-pair · gpt-3.5-turbo

key terms related to arguments, issues, and decision-making processes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Traps

-0.64

abella

-0.60

 fitt

-0.60

irie

-0.60

ritz

-0.59

bats

-0.59

ollo

-0.58

 chambers

-0.57

 clipboard

-0.57

dimension

-0.56

POSITIVE LOGITS

 unto

0.74

 akin

0.69

 indeed

0.66

 attRot

0.66

 nonetheless

0.65

uristic

0.65

 worthy

0.64

 wedd

0.64

"}],"

0.62

 punishable

0.62

Activations Density 0.342%

phrases expressing challenges, debates, and decisive situations

key terms related to arguments, issues, and decision-making processes

No Comments

No Known Activations