INDEX

Explanations

phrases related to actions or discussions happening behind the scenes

oai_token-act-pair · gpt-3.5-turbo

references to "behind the scenes" in various contexts

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

 aloud

-0.73

RIC

-0.73

fully

-0.73

 anew

-0.69

 msec

-0.65

QL

-0.64

 unfocusedRange

-0.64

arily

-0.61

 alum

-0.59

mun

-0.57

POSITIVE LOGITS

 scenes

0.84

 curtain

0.82

 Scenes

0.77

clock

0.77

facade

0.67

scene

0.67

 veil

0.66

 firewall

0.65

 doors

0.64

ãģĨ

0.64

Activations Density 0.112%

phrases related to actions or discussions happening behind the scenes

references to "behind the scenes" in various contexts

No Comments

No Known Activations