INDEX

Explanations

terms related to the word "weed" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to "weed," particularly in the context of its use and implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ultz

-0.78

*/(

-0.69

uras

-0.66

erald

-0.66

riel

-0.65

abol

-0.63

ctic

-0.62

":["

-0.62

ocal

-0.62

nz

-0.61

POSITIVE LOGITS

 weed

1.11

 Weed

0.88

weed

0.87

killer

0.86

atio

0.84

 weeds

0.83

killers

0.81

aceous

0.81

bowl

0.80

 buds

0.77

Activations Density 0.009%

terms related to the word "weed" in various contexts

references to "weed," particularly in the context of its use and implications

No Comments

No Known Activations