INDEX

Explanations

instances of the word "one" and potentially phrases related to comparison or selection

oai_token-act-pair · gpt-3.5-turbo

repetitions of the word "one" 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

emies

-0.85

zos

-0.81

enegger

-0.81

ãĤ¤ãĥĪ

-0.79

ears

-0.76

ernels

-0.76

osponsors

-0.72

groups

-0.72

needs

-0.71

actions

-0.71

POSITIVE LOGITS

 stroke

1.00

 embodiment

0.99

 instance

0.95

 swoop

0.87

 iteration

0.85

 fell

0.85

of

0.84

 sentence

0.83

 piece

0.82

 respect

0.82

Activations Density 0.050%

instances of the word "one" and potentially phrases related to comparison or selection

repetitions of the word "one" in various contexts

No Comments

No Known Activations