INDEX

Explanations

text containing the concept of backward actions or states

oai_token-act-pair · gpt-3.5-turbo

terms related to movement in reverse or backward actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Flavoring

-0.70

ndra

-0.68

AFP

-0.67

cade

-0.65

 House

-0.63

 Photographer

-0.63

LCS

-0.63

onis

-0.63

 Consulting

-0.61

Gle

-0.59

POSITIVE LOGITS

 backwards

4.00

 backward

4.00

 sideways

1.54

 forwards

1.34

 forward

1.28

 downwards

1.15

 downward

1.12

 Forward

1.11

Forward

1.08

 regress

1.04

Activations Density 0.014%

text containing the concept of backward actions or states

terms related to movement in reverse or backward actions

No Comments

No Known Activations