INDEX

Explanations

words related to actions that involve control, alteration, or influence

oai_token-act-pair · gpt-3.5-turbo

gerunds and present participles, indicating ongoing actions or 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

omet

-0.69

spot

-0.67

eva

-0.63

sv

-0.62

 flowing

-0.61

 cropped

-0.58

 flown

-0.57

behind

-0.57

unc

-0.57

fur

-0.56

POSITIVE LOGITS

redients

1.02

HAM

0.87

tons

0.83

aukee

0.82

ADRA

0.78

utical

0.77

ulate

0.76

pole

0.76

enance

0.75

rarily

0.73

Activations Density 0.110%

words related to actions that involve control, alteration, or influence

gerunds and present participles, indicating ongoing actions or processes

No Comments

No Known Activations