INDEX

Explanations

the word "basically" or similar words indicating a simplification or summarization

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate simplifications or generalizations of complex concepts

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

alez

-0.78

Ey

-0.74

Others

-0.71

rer

-0.70

Tickets

-0.70

encers

-0.66

eful

-0.64

ttp

-0.63

TERN

-0.63

ificantly

-0.63

POSITIVE LOGITS

 worthless

0.84

 meaningless

0.79

 useless

0.77

 unus

0.74

 boils

0.73

 lifeless

0.72

unin

0.71

 unchanged

0.69

 indistinguishable

0.66

strate

0.65

Activations Density 0.027%

the word "basically" or similar words indicating a simplification or summarization

phrases that indicate simplifications or generalizations of complex concepts

No Comments

No Known Activations