INDEX

Explanations

software or computer-related terms, particularly those related to processes

oai_token-act-pair · gpt-3.5-turbo

terms related to processing and workflows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

gged

-0.78

azo

-0.74

 Haram

-0.73

aez

-0.72

legged

-0.71

lar

-0.66

gdala

-0.65

glers

-0.65

 Fighters

-0.65

geon

-0.63

POSITIVE LOGITS

ional

1.06

ions

0.98

ors

0.83

ivity

0.82

amins

0.77

ivism

0.75

Hunt

0.75

ioned

0.74

inct

0.73

 Process

0.71

Activations Density 0.022%

software or computer-related terms, particularly those related to processes

terms related to processing and workflows

No Comments

No Known Activations