INDEX

Explanations

objects or entities that are described as being at the top or uppermost level of a hierarchy

oai_token-act-pair · gpt-3.5-turbo

terms related to hierarchical rankings or classifications

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

PsyNetMessage

-0.75

ndum

-0.66

interrupted

-0.60

rities

-0.59

urgy

-0.59

ryu

-0.57

 Paraly

-0.55

 tears

-0.55

tm

-0.55

ãĤ¶

-0.54

POSITIVE LOGITS

 earners

0.79

 drawer

0.77

 notch

0.71

ranking

0.69

Tier

0.69

draw

0.68

lining

0.67

nings

0.66

 contender

0.65

 priority

0.64

Activations Density 0.082%

objects or entities that are described as being at the top or uppermost level of a hierarchy

terms related to hierarchical rankings or classifications

No Comments

No Known Activations