INDEX

Explanations

phrases related to taking actions against someone or something

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "take down."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

inen

-0.78

athi

-0.74

0000000000000000

-0.69

ĸļ

-0.69

uno

-0.67

Streamer

-0.66

yne

-0.65

ira

-0.63

¶ħ

-0.63

ï¿½ï¿½

-0.63

POSITIVE LOGITS

 stairs

1.02

grading

0.77

stairs

0.74

 weeds

0.73

graded

0.72

 stakes

0.72

 clipboard

0.71

 notices

0.71

river

0.68

 hill

0.67

Activations Density 0.023%

phrases related to taking actions against someone or something

instances of the phrase "take down."

No Comments

No Known Activations