INDEX

Explanations

words related to imposing control or restriction

oai_token-act-pair · gpt-3.5-turbo

terms related to controlling or limiting certain actions, behaviors, or conditions

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

akia

-0.71

akin

-0.69

 Kinnikuman

-0.68

atched

-0.67

 Sacrament

-0.67

 Nare

-0.66

ovember

-0.65

Eps

-0.64

aked

-0.64

arily

-0.63

POSITIVE LOGITS

ãĥį

0.80

reon

0.75

 curb

0.75

 stomp

0.74

rence

0.73

side

0.73

 bowling

0.72

 actionGroup

0.70

pick

0.70

ried

0.70

Activations Density 0.018%

words related to imposing control or restriction

terms related to controlling or limiting certain actions, behaviors, or conditions

No Comments

No Known Activations