INDEX

Explanations

specific mentions of the letter "T" with high activation values

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "T" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.81

 cannabin

-0.76

 actionGroup

-0.75

EStream

-0.74

 ment

-0.70

ħĭ

-0.67

 destro

-0.66

-0.62

 gorilla

-0.62

 diapers

-0.62

POSITIVE LOGITS

ARGET

1.24

ribute

1.19

ributes

1.13

olerance

1.12

ractor

1.10

ract

1.07

ruck

1.05

agged

1.05

unes

1.04

uple

1.04

Activations Density 0.082%

specific mentions of the letter "T" with high activation values

occurrences of the letter "T" in various forms

No Comments

No Known Activations