INDEX

Explanations

phrases related to suspicion or pretense

oai_token-act-pair · gpt-3.5-turbo

words related to suspicion or pretense

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.78

SHIP

-0.72

EngineDebug

-0.70

ORGE

-0.70

bian

-0.68

è£ħ

-0.67

gow

-0.67

¿½

-0.67

[|

-0.67

WER

-0.65

POSITIVE LOGITS

ension

1.34

ended

1.33

ensions

1.32

icious

1.20

icit

1.10

ensive

1.09

enders

1.08

endant

1.07

ugal

1.07

ices

1.05

Activations Density 0.043%

phrases related to suspicion or pretense

words related to suspicion or pretense

No Comments

No Known Activations