INDEX

Explanations

words related to demonstrating or proving something

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "prove" and its variations, indicating an emphasis on demonstrating capability or validation

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

 newsletters

-0.74

ummer

-0.65

ufact

-0.64

ropri

-0.64

letal

-0.64

 liner

-0.63

EStreamFrame

-0.61

alez

-0.59

 contrace

-0.59

ovo

-0.57

POSITIVE LOGITS

\\\\\\\\

0.86

reader

0.82

||||

0.72

 proves

0.69

Ø³

0.69

Â¯Â¯

0.68

stal

0.68

mount

0.68

 Grounds

0.68

 prove

0.68

Activations Density 0.018%

words related to demonstrating or proving something

instances of the verb "prove" and its variations, indicating an emphasis on demonstrating capability or validation

No Comments

No Known Activations