INDEX

Explanations

statements where there is an indication or feeling conveyed

oai_token-act-pair · gpt-3.5-turbo

phrases that express a sense of conjecture or speculation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rouse

-0.91

otos

-0.84

venge

-0.79

orem

-0.73

atching

-0.73

ests

-0.73

izons

-0.72

andise

-0.71

iling

-0.71

umbn

-0.69

POSITIVE LOGITS

 unfair

0.81

 doubtful

0.74

ãĤ¨

0.74

 unlikely

0.72

 unclear

0.71

 probable

0.71

ril

0.68

 imperative

0.68

 Chimera

0.67

 abundantly

0.66

Activations Density 0.049%

statements where there is an indication or feeling conveyed

phrases that express a sense of conjecture or speculation

No Comments

No Known Activations