INDEX

Explanations

words related to performance, comparison, and achievement

oai_token-act-pair · gpt-3.5-turbo

terms related to performance evaluations

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

umb

-0.68

hal

-0.66

origin

-0.65

Closure

-0.65

rel

-0.64

ãĥĨãĤ£

-0.62

 origin

-0.61

 coll

-0.60

SI

-0.59

arc

-0.59

POSITIVE LOGITS

ients

0.87

 miser

0.86

nces

0.85

luster

0.84

 prospects

0.82

 academ

0.79

 financially

0.79

 successes

0.76

 fared

0.75

 economically

0.74

Activations Density 0.169%

words related to performance, comparison, and achievement

terms related to performance evaluations

No Comments

No Known Activations