INDEX

Explanations

adjectives and adverbs related to past events or conditions

oai_token-act-pair · gpt-3.5-turbo

references to past experiences and lessons learned

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

orah

-0.74

rodu

-0.65

artifacts

-0.65

ersed

-0.65

 PLEASE

-0.64

iameter

-0.64

verett

-0.63

oris

-0.62

yout

-0.61

ilial

-0.61

POSITIVE LOGITS

 previous

1.12

 inception

0.91

 predecessors

0.84

 prior

0.76

 earlier

0.76

 past

0.76

 preceding

0.74

 predecessor

0.71

 childhood

0.69

 last

0.69

Activations Density 0.518%

adjectives and adverbs related to past events or conditions

references to past experiences and lessons learned

No Comments

No Known Activations