INDEX

Explanations

occurrences of the word "Ka" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Ka" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ttes

-0.78

tti

-0.69

lessly

-0.67

tons

-0.63

ROR

-0.60

ABE

-0.60

wcsstore

-0.58

 Tillerson

-0.56

rers

-0.56

ently

-0.56

POSITIVE LOGITS

iser

1.28

isers

1.14

plan

1.10

pler

1.10

oru

1.04

iba

1.02

izer

0.99

iley

0.95

ichi

0.93

emia

0.93

Activations Density 0.048%

occurrences of the word "Ka" followed by a numerical value

occurrences of the name "Ka" in various contexts

No Comments

No Known Activations