INDEX

Explanations

verbs related to giving a clear definition or description

oai_token-act-pair · gpt-3.5-turbo

instances of the word "define" and its variations, indicating discussions about definitions and distinctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rites

-0.77

ublic

-0.67

osate

-0.66

lot

-0.65

enos

-0.65

visor

-0.64

riel

-0.64

orah

-0.63

ittle

-0.63

ience

-0.62

POSITIVE LOGITS

 boundaries

0.93

initions

0.90

 parameters

0.85

 criteria

0.83

 definitions

0.81

 thresholds

0.77

 defines

0.76

 exactly

0.76

 defining

0.74

 roles

0.74

Activations Density 0.074%

verbs related to giving a clear definition or description

instances of the word "define" and its variations, indicating discussions about definitions and distinctions

No Comments

No Known Activations