INDEX

Explanations

repetitive occurrences of the string "ub" followed by a high activation value of 9 or 10

oai_token-act-pair · gpt-3.5-turbo

variations of the word "ub."

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

Negative Logits

ensis

-0.67

Lan

-0.64

 onto

-0.61

 arrivals

-0.59

 Victims

-0.59

 incomes

-0.58

EMENT

-0.58

 Crimes

-0.58

 Leaving

-0.58

 assists

-0.57

POSITIVE LOGITS

ub

4.35

ubs

2.78

UB

2.15

ubi

2.04

ubes

1.94

ube

1.85

uble

1.77

ubb

1.77

uber

1.70

uba

1.57

Activations Density 0.013%

repetitive occurrences of the string "ub" followed by a high activation value of 9 or 10

variations of the word "ub."

No Known Activations