INDEX

Explanations

words related to drawing conclusions or making judgments

oai_token-act-pair · gpt-3.5-turbo

references to conclusions or outcomes of reasoning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

skill

-0.71

ophon

-0.70

 Leban

-0.65

inventory

-0.64

amen

-0.64

names

-0.63

nas

-0.62

ansk

-0.62

akin

-0.61

bey

-0.61

POSITIVE LOGITS

 conclusions

1.01

 conclusion

0.94

abl

0.86

 drawn

0.82

 regarding

0.79

 based

0.77

éĸ

0.77

0.75

igm

0.74

lessly

0.73

Activations Density 0.054%

words related to drawing conclusions or making judgments

references to conclusions or outcomes of reasoning

No Comments

No Known Activations