INDEX

Explanations

the word "Fu" at various activation levels, possibly associated with names or locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Fu," often associated with specific individuals or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

*/(

-0.85

apy

-0.77

sburgh

-0.76

theless

-0.73

 Orbit

-0.71

lihood

-0.71

 Turing

-0.69

 Remastered

-0.68

 Emin

-0.68

ãģĨ

-0.68

POSITIVE LOGITS

selage

1.62

lda

1.19

jin

1.07

ged

0.93

cci

0.89

ueless

0.89

ugi

0.89

qua

0.85

emen

0.85

ÃŁ

0.85

Activations Density 0.035%

the word "Fu" at various activation levels, possibly associated with names or locations

occurrences of the term "Fu," often associated with specific individuals or contexts

No Comments

No Known Activations