INDEX

Explanations

mentions of inadequacy, insufficiency, or not meeting requirements in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to inadequacy 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 @ 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

dar

-0.81

cow

-0.77

aptic

-0.76

dot

-0.72

da

-0.70

saw

-0.70

âĸ¬

-0.70

=-=-=-=-

-0.69

=-=-=-=-=-=-=-=-

-0.68

POSITIVE LOGITS

mble

0.86

intendent

0.84

ufficient

0.83

 accommodations

0.79

 remed

0.79

 adequate

0.78

 accommodation

0.77

 adequately

0.77

adequ

0.76

 adequ

0.76

Activations Density 0.021%

mentions of inadequacy, insufficiency, or not meeting requirements in various contexts

terms related to inadequacy in various contexts

No Comments

No Known Activations