INDEX

Explanations

specific phrases related to organized groups or structures, specifically involving a hierarchical structure with "and file" being the most prominent

oai_token-act-pair · gpt-3.5-turbo

terms related to evaluations or assessments of groups or activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

skill

-0.77

Chat

-0.68

Tag

-0.67

 Scan

-0.67

 Username

-0.66

say

-0.66

Spot

-0.63

idel

-0.63

Osw

-0.63

SN

-0.62

POSITIVE LOGITS

 iceberg

0.82

 fallacy

0.69

eer

0.66

rollers

0.65

 boosters

0.65

âĦ¢:

0.62

legates

0.62

 supervisors

0.62

 hindsight

0.62

 debacle

0.61

Activations Density 0.486%

specific phrases related to organized groups or structures, specifically involving a hierarchical structure with "and file" being the most prominent

terms related to evaluations or assessments of groups or activities

No Comments

No Known Activations